Linux & AI/Alife
mini-HOWTO

Version 2.0

This document is maintained by John A. Eikenberry
The master page for this document is http://www.ai.uga.edu/~jae/ai.html
Last modified: Tue Jan 13 17:23:21 EST 1998


Table of Contents

  • What's New
  • Introduction
  • Programming Languages
  • Traditional Artificial Intelligence
  • Connectionism (neural nets)
  • Evolutionary Computing (EC) (genetic algorithms/programming)
  • Artificial Life
  • Autonomous Agents and Bots
  • AI & Alife related newsgroups
  • AI & Alife resource links

  • What's New

    Note: For a list of new additions to this mini-howto, please visit the
    master page listed above.

    (1.11.98)Thanks to Dirk Heise for his submission of Gas. I've also removed a couple more of the non-AI oriented scheme implementations. I just felt having 10 scheme implementations listed was a bit silly, especially since some of them weren't really meant for AI stuff. If you want a listing of more scheme's look here or here.

    (12.29.97) Added a couple more entries and web links, including a patched lil-gp.

    (10.1.97) Ok. I struck the motherload of Baysean Networks, see the Connectionism section for more. Plus I cleaned off the 'New' flags from anything before August.

    (9.26.97) The reformat is done! :) If you are reading this somewhere other than the master page, please take a look and let me know what you think. Now I can get back to work on my thesis...

    Purpose

    The Linux OS has evolved from its origins in hackerdom to a full blown UNIX, capable of rivaling any commercial UNIX. It now provides an inexpensive base to build a great workstation. It has shed its hardware dependencies, having been ported to DEC Alphas, Sparcs, PowerPCs, with others on the way. This potential speed boost along with its networking support will make it great for workstation clusters. As a workstation it allows for all sorts of research and development, including artificial intelligence and artificial life.

    The purpose of this Mini-Howto is to provide a source to find out about various software packages, code libraries, and anything else that will help someone get started working with (and find resources for) artificial intelligence and artificial life. All done with Linux specifically in mind.

    Where to find this software

    All this software should be available via the net (ftp || http). The links to where to find it will be provided in the description of each package. There will also be plenty of software not covered on these pages (which is usually platform independent) located on one of the resources listed under the
    Web Links section.

    Updates and comments

    If you find any mistakes, know of updates to one of the items below, or have problems compiling and of the applications, please mail me at:
    jae@ai.uga.edu and I'll see what I can do.

    If you know of any AI/Alife applications, class libraries, etc. Please email me about them. Include your name, ftp and/or http sites where they can be found, plus a brief overview/commentary on the software (this info would make things a lot easier on me... but don't feel obligated ;).

    I know that keeping this list up to date and expanding it will take quite a bit of work. So please be patient (I do have other projects). I hope you will find this document helpful.


    Programming languages

    While any programming language can be used for artificial intelligence/life research, these are programming languages which are used extensively for, if not specifically made for, artificial intelligence programming.

    ECoLisp [New]
    Web site:
    www.di.unipi.it/~attardi/software.html
    ECoLisp (Embeddable Common Lisp) is an implementation of Common Lisp designed for being embeddable into C based applications. ECL uses standard C calling conventions for Lisp compiled functions, which allows C programs to easily call Lisp functions and viceversa. No foreign function interface is required: data can be exchanged between C and Lisp with no need for conversion. ECL is based on a Common Runtime Support (CRS) which provides basic facilities for memory managment, dynamic loading and dumping of binary images, support for multiple threads of execution. The CRS is built into a library that can be linked with the code of the application. ECL is modular: main modules are the program development tools (top level, debugger, trace, stepper), the compiler, and CLOS. A native implementation of CLOS is available in ECL: one can configure ECL with or without CLOS. A runtime version of ECL can be built with just the modules which are required by the application. The ECL compiler compiles from Lisp to C, and then invokes the GCC compiler to produce binaries.

    Gödel
    Web page:
    www.cs.bris.ac.uk/~bowers/goedel.html
    Gödel is a declarative, general-purpose programming language in the family of logic programming languages. It is a strongly typed language, the type system being based on many-sorted logic with parametric polymorphism. It has a module system. Gödel supports infinite precision integers, infinite precision rationals, and also floating-point numbers. It can solve constraints over finite domains of integers and also linear rational constraints. It supports processing of finite sets. It also has a flexible computation rule and a pruning operator which generalizes the commit of the concurrent logic programming languages. Considerable emphasis is placed on Gödel's meta- logical facilities which provide significant support for meta-programs that do analysis, transformation, compilation, verification, debugging, and so on.

    LIFE
    Web page:
    www.isg.sfu.ca/life
    LIFE (Logic, Inheritance, Functions, and Equations) is an experimental programming language proposing to integrate three orthogonal programming paradigms proven useful for symbolic computation. From the programmer's standpoint, it may be perceived as a language taking after logic programming, functional programming, and object-oriented programming. From a formal perspective, it may be seen as an instance (or rather, a composition of three instances) of a Constraint Logic Programming scheme due to Hoehfeld and Smolka refining that of Jaffar and Lassez.

    CLisp (Lisp)
    FTP site:
    sunsite.unc.edu/pub/Linux/devel/lang/lisp/
    CLISP is a Common Lisp implementation by Bruno Haible and Michael Stoll. It mostly supports the Lisp described by 'Common LISP: The Language (2nd edition)' and the ANSI Common Lisp standard. CLISP includes an interpreter, a byte-compiler, a large subset of CLOS (Object-Oriented Lisp) , a foreign language interface and, for some machines, a screen editor.

    The user interface language (English, German, French) is chosen at run time. Major packages that run in CLISP include CLX & Garnet. CLISP needs only 2 MB of memory.

    CMU Common Lisp
    Web page:
    www.mv.com/users/pw/lisp/index.html
    FTP site: sunsite.unc.edu/pub/Linux/devel/lang/lisp/
    CMU Common Lisp is a public domain "industrial strength" Common Lisp programming environment. Many of the X3j13 changes have been incorporated into CMU CL. Wherever possible, this has been done so as to transparently allow the use of either CLtL1 or proposed ANSI CL. Probably the new features most interesting to users are SETF functions, LOOP and the WITH-COMPILATION-UNIT macro.

    GCL (Lisp)
    FTP site:
    sunsite.unc.edu/pub/Linux/devel/lang/lisp/
    GNU Common Lisp (GCL) has a compiler and interpreter for Common Lisp. It used to be known as Kyoto Common Lisp. It is very portable and extremely efficient on a wide class of applications. It compares favorably in performance with commercial Lisps on several large theorem-prover and symbolic algebra systems. It supports the CLtL1 specification but is moving towards the proposed ANSI definition. GCL compiles to C and then uses the native optimizing C compilers (e.g., GCC). A function with a fixed number of args and one value turns into a C function of the same number of args, returning one value, so GCL is maximally efficient on such calls. It has a conservative garbage collector which allows great freedom for the C compiler to put Lisp values in arbitrary registers.

    It has a source level Lisp debugger for interpreted code, with display of source code in an Emacs window. Its profiling tools (based on the C profiling tools) count function calls and the time spent in each function.

    Mercury
    Web page:
    www.cs.mu.oz.au/research/mercury/
    Mercury is a new, purely declarative logic programming language. Like Prolog and other existing logic programming languages, it is a very high-level language that allows programmers to concentrate on the problem rather than the low-level details such as memory management. Unlike Prolog, which is oriented towards exploratory programming, Mercury is designed for the construction of large, reliable, efficient software systems by teams of programmers. As a consequence, programming in Mercury has a different flavor than programming in Prolog.

    DFKI OZ
    Web page:
    www.ps.uni-sb.de/oz/
    FTP site: ps-ftp.dfki.uni-sb.de/pub/oz2/
    Oz is a high-level programming language designed for concurrent symbolic computation. It is based on a new computation model providing a uniform and simple foundation for several programming paradigms, including higher-order functional, constraint logic, and concurrent object-oriented programming. Oz is designed as a successor to languages such as Lisp, Prolog and Smalltalk, which fail to support applications that require concurrency, reactivity, and real-time control.

    DFKI Oz is an interactive implementation of Oz featuring a programming interface based on GNU Emacs, a concurrent browser, an object-oriented interface to Tcl/Tk, powerful interoperability features (sockets, C, C++), an incremental compiler, a garbage collector, and support for stand-alone applications. Performance is competitive with commercial Prolog and Lisp systems.

    BinProlog
    Web site(documentation):
    clement.info.umoncton.ca/BinProlog/UNCOMPRESSED/doc/html/art.html
    FTP site(source): clement.info.umoncton.ca/BinProlog
    FTP site(binary): clement.info.umoncton.ca/BinProlog/UNCOMPRESSED/bin
    BinProlog is a fast and compact Prolog compiler, based on the transformation of Prolog to binary clauses. The compilation technique is similar to the Continuation Passing Style transformation used in some ML implementations. BinProlog 5.00 is also probably the first Prolog system featuring dynamic recompilation of asserted predicates (a technique similar to the one used in some object oriented languages like SELF 4.0), and a very efficient segment preserving copying heap garbage collector.

    Although it (used to) incorporate some last minute research experiments, which might look adventurous at the first sight, BinProlog is a fairly robust and complete Prolog implementation featuring both C-emulated execution and generation of stand-alone applications by compilation to C.

    SWI Prolog
    Web page:
    swi.psy.uva.nl/projects/xpce/SWI-Prolog.html
    FTP site: swi.psy.uva.nl/pub/SWI-Prolog/
    SWI is a free version of prolog in the Edinburgh Prolog family (thus making it very similar to Quintus and many other versions). With: a large library of built in predicates, a module system, garbage collection, a two-way interface with the C language, plus many other features. It is meant as a educational language, so it's compiled code isn't the fastest. Although it similarity to Quintus allows for easy porting.

    XPCE is freely available in binary form for the Linux version of SWI-prolog. XPCE is an object oriented X-windows GUI development package/environment.

    Kali Scheme
    Web site:
    www.neci.nj.nec.com/PLS/Kali.html
    Kali Scheme is a distributed implementation of Scheme that permits efficient transmission of higher-order objects such as closures and continuations. The integration of distributed communication facilities within a higher-order programming language engenders a number of new abstractions and paradigms for distributed computing. Among these are user-specified load-balancing and migration policies for threads, incrementally-linked distributed computations, agents, and parameterized client-server applications. Kali Scheme supports concurrency and communication using first-class procedures and continuations. It integrates procedures and continuations into a message-based distributed framework that allows any Scheme object (including code vectors) to be sent and received in a message.

    RScheme
    Web site:
    www.rosette.com/~donovan/rs/rscheme.html
    FTP site: ftp.rosette.com/pub/rscheme
    RScheme is an object-oriented, extended version of the Scheme dialect of Lisp. RScheme is freely redistributable, and offers reasonable performance despite being extraordinarily portable. RScheme can be compiled to C, and the C can then compiled with a normal C compiler to generate machine code. By default, however, RScheme compiles to bytecodes which are interpreted by a (runtime) virtual machine. This ensures that compilation is fast and keeps code size down. In general, we recommend using the (default) bytecode code generation system, and only compiling your time-critical code to machine code. This allows a nice adjustment of space/time tradeoffs. (see web site for details)

    Scheme48
    Web site:
    www-swiss.ai.mit.edu/~jar/s48.html (download from ftp site)
    FTP site: swiss-ftp.ai.mit.edu:/archive/s48/
    Scheme 48 is a Scheme implementation based on a virtual machine architecture. Scheme 48 is designed to be straightforward, flexible, reliable, and fast. It should be easily portable to 32-bit byte-addressed machines that have POSIX and ANSI C support. In addition to the usual Scheme built-in procedures and a development environment, library software includes support for hygienic macros (as described in the Revised^4 Scheme report), multitasking, records, exception handling, hash tables, arrays, weak pointers, and FORMAT. Scheme 48 implements and exploits an experimental module system loosely derived from Standard ML and Scheme Xerox. The development environment supports interactive changes to modules and interfaces.

    SCM (Scheme)
    Web site:
    www-swiss.ai.mit.edu/~jaffer/SCM.html
    FTP site: swiss-ftp.ai.mit.edu:/archive/scm/
    SCM conforms to the Revised^4 Report on the Algorithmic Language Scheme and the IEEE P1178 specification. Scm is written in C. It uses the following utilities (all available at the ftp site).

    Shift [New]
    Web site:
    www.path.berkeley.edu/shift/
    Shift is a programming language for describing dynamic networks of hybrid automata. Such systems consist of components which can be created, interconnected and destroyed as the system evolves. Components exhibit hybrid behavior, consisting of continuous-time phases separated by discrete-event transitions. Components may evolve independently, or they may interact through their inputs, outputs and exported events. The interaction network itself may evolve.

    Traditional Artificial Intelligence

    Traditional AI is based around the ideas of logic, rule systems, linguistics, and the concept of rationality. At its roots are programming languages such as Lisp and Prolog. Expert systems are the largest successful example of this paradigm. An expert system consists of a detailed knowledge base and a complex rule system to utilize it. Such systems have been used for such things as medical diagnosis support and credit checking systems.

    AI class/code libraries

    These are libraries of code or classes for use in programming within the artificial intelligence field. They are not meant as stand alone applications, but rather as tools for building your own applications.

    AI Search
    FTP site:
    ftp.icce.rug.nl/pub/peter/
    Submitted by: Peter M. Bouthoorn
    Basically, the library offers the programmer a set of search algorithms that may be used to solve all kind of different problems. The idea is that when developing problem solving software the programmer should be able to concentrate on the representation of the problem to be solved and should not need to bother with the implementation of the search algorithm that will be used to actually conduct the search. This idea has been realized by the implementation of a set of search classes that may be incorporated in other software through C++'s features of derivation and inheritance. The following search algorithms have been implemented:

    - depth-first tree and graph search.
    - breadth-first tree and graph search.
    - uniform-cost tree and graph search.
    - best-first search.
    - bidirectional depth-first tree and graph search.
    - bidirectional breadth-first tree and graph search.
    - AND/OR depth tree search.
    - AND/OR breadth tree search.

    Peter plans to release a new version of the library soon, which will also be featured in a book about C++ and AI to appear this year.

    Chess In Lisp (CIL)
    FTP site:
    chess.onenet.net/pub/chess/uploads/projects/
    The CIL (Chess In Lisp) foundation is a Common Lisp implementaion of all the core functions needed for development of chess applications. The main purpose of the CIL project is to get AI researchers interested in using Lisp to work in the chess domain.

    DAI [New]
    Web site:
    starship.skyport.net/crew/gandalf/DNET/AI
    A library for the Python programming language that provides an object oriented interface to the CLIPS expert system tool. It includes an interface to COOL (CLIPS Object Oriented Language) that allows:

    Nyquist [New]
    Web site:
    www.cs.cmu.edu/afs/cs.cmu.edu/project/music/web/music.html
    The Computer Music Project at CMU is developing computer music and interactive performance technology to enhance human musical experience and creativity. This interdisciplinary effort draws on Music Theory, Cognitive Science, Artificial Intelligence and Machine Learning, Human Computer Interaction, Real-Time Systems, Computer Graphics and Animation, Multimedia, Programming Languages, and Signal Processing. A paradigmatic example of these interdisciplinary efforts is the creation of interactive performances that couple human musical improvisation with intelligent computer agents in real-time.

    Screamer
    Web site:
    www.cis.upenn.edu/~screamer-tools/home.html
    Screamer is an extension of Common Lisp that adds support for nondeterministic programming. Screamer consists of two levels. The basic nondeterministic level adds support for backtracking and undoable side effects. On top of this nondeterministic substrate, Screamer provides a comprehensive constraint programming language in which one can formulate and solve mixed systems of numeric and symbolic constraints. Together, these two levels augment Common Lisp with practically all of the functionality of both Prolog and constraint logic programming languages such as CHiP and CLP(R). Furthermore, Screamer is fully integrated with Common Lisp. Screamer programs can coexist and interoperate with other extensions to Common Lisp such as CLOS, CLIM and Iterate.

    AI software kits, applications, etc.

    These are various applications, software kits, etc. meant for research in the field of artificial intelligence. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package.
    ASA - Adaptive Simulated Annealing
    Web site:
    www.ingber.com/#ASA-CODE
    FTP site: ftp.ingber.com/
    ASA (Adaptive Simulated Annealing) is a powerful global optimization C-code algorithm especially useful for nonlinear and/or stochastic systems.

    ASA is developed to statistically find the best global fit of a nonlinear non-convex cost-function over a D-dimensional space. This algorithm permits an annealing schedule for 'temperature' T decreasing exponentially in annealing-time k, T = T_0 exp(-c k^1/D). The introduction of re-annealing also permits adaptation to changing sensitivities in the multi-dimensional parameter-space. This annealing schedule is faster than fast Cauchy annealing, where T = T_0/k, and much faster than Boltzmann annealing, where T = T_0/ln k.

    Babylon
    FTP site:
    ftp.gmd.de/gmd/ai-research/Software/Babylon/
    BABYLON is a modular, configurable, hybrid environment for developing expert systems. Its features include objects, rules with forward and backward chaining, logic (Prolog) and constraints. BABYLON is implemented and embedded in Common Lisp.

    CLEARS
    Web site:
    www.coli.uni-sb.de/~clears/
    The CLEARS system is an interactive graphical environment for computational semantics. The tool allows exploration and comparison of different semantic formalisms, and their interaction with syntax. This enables the user to get an idea of the range of possibilities of semantic construction, and also where there is real convergence between theories.

    CLIPS
    Web site:
    www.jsc.nasa.gov/~clips/CLIPS.html
    FTP site: cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/areas/expert/systems/clips
    CLIPS is a productive development and delivery expert system tool which provides a complete environment for the construction of rule and/or object based expert systems.

    CLIPS provides a cohesive tool for handling a wide variety of knowledge with support for three different programming paradigms: rule-based, object-oriented and procedural. Rule-based programming allows knowledge to be represented as heuristics, or "rules of thumb," which specify a set of actions to be performed for a given situation. Object-oriented programming allows complex systems to be modeled as modular components (which can be easily reused to model other systems or to create new components). The procedural programming capabilities provided by CLIPS are similar to capabilities found in languages such as C, Pascal, Ada, and LISP.

    EMA-XPS - A Hybrid Graphic Expert System Shell
    Web site:
    wmwap1.math.uni-wuppertal.de:80/EMA-XPS/
    EMA-XPS is a hybrid graphic expert system shell based on the ASCII-oriented shell Babylon 2.3 of the German National Research Center for Computer Sciences (GMD). In addition to Babylon's AI-power (object oriented data representation, forward and backward chained rules - collectible into sets, horn clauses, and constraint networks) a graphic interface based on the X11 Window System and the OSF/Motif Widget Library has been provided.

    FOOL & FOX
    FTP site:
    ntia.its.bldrdoc.gov/pub/fuzzy/prog/
    FOOL stands for the Fuzzy Organizer OLdenburg. It is a result from a project at the University of Oldenburg. FOOL is a graphical user interface to develop fuzzy rulebases. FOOL will help you to invent and maintain a database that specifies the behavior of a fuzzy-controller or something like that.

    FOX is a small but powerful fuzzy engine which reads this database, reads some input values and calculates the new control value.

    FUF and SURGE
    Web site:
    www.dfki.de/lt/registry/generation/fuf.html
    FTP site: ftp.cs.columbia.edu/pub/fuf/
    FUF is an extended implementation of the formalism of functional unification grammars (FUGs) introduced by Martin Kay specialized to the task of natural language generation. It adds the following features to the base formalism: These extensions allow the development of large grammars which can be processed efficiently and can be maintained and understood more easily. SURGE is a large syntactic realization grammar of English written in FUF. SURGE is developed to serve as a black box syntactic generation component in a larger generation system that encapsulates a rich knowledge of English syntax. SURGE can also be used as a platform for exploration of grammar writing with a generation perspective.

    The Grammar Workbench
    Web site:
    www.cs.kun.nl/agfl/GWB.html
    The Grammar Workbench, or GWB for short, is an environment for the comfortable development of Affix Grammars in the AGFL-formalism. Its purposes are:

    GSM Suite [New]
    Web site:
    www.slip.net/~andrewm/gsm/
    The GSM Suite is a set of programs for using Finite State Machines in a graphical fashion. The suite consists of programs that edit, compile, and print state machines. Included in the suite is an editor program, gsmedit, a compiler, gsm2cc, that produces a C++ implementation of a state machine, a PostScript generator, gsm2ps, and two other minor programs. GSM is licensed under the GNU Public License and so is free for your use under the terms of that license.

    Illuminator
    Web site:
    documents.cfar.umd.edu/resources/source/illuminator.html
    Illuminator is a toolset for developing OCR and Image Understanding applications. Illuminator has two major parts: a library for representing, storing and retrieving OCR information, heretofore called dafslib, and an X-Windows "DAFS" file viewer, called illum. Illuminator and DAFS lib were designed to supplant existing OCR formats and become a standard in the industry. They particularly are extensible to handle more than just English. The features of this release:

    Jess, the Java Expert System Shell
    Web site:
    herzberg.ca.sandia.gov/jess/
    Jess is a clone of the popular CLIPS expert system shell written entirely in Java. With Jess, you can conveniently give your applets the ability to 'reason'. Jess is compatible with all versions of Java starting with version 1.0.2. Jess implements the following constructs from CLIPS: defrules, deffunctions, defglobals, deffacts, and deftemplates.

    learn
    FTP site:
    sunsite.unc.edu/pub/Linux/apps/cai/
    Learn is a vocable learning program with memory model.

    Otter: An Automated Deduction System
    Web site:
    www.mcs.anl.gov/home/mccune/ar/otter
    Our current automated deduction system Otter is designed to prove theorems stated in first-order logic with equality. Otter's inference rules are based on resolution and paramodulation, and it includes facilities for term rewriting, term orderings, Knuth-Bendix completion, weighting, and strategies for directing and restricting searches for proofs. Otter can also be used as a symbolic calculator and has an embedded equational programming system.

    RIPPER
    Web site:
    www.research.att.com/~wcohen/ripperd.html
    Ripper is a system for fast effective rule induction. Given a set of data, Ripper will learn a set of rules that will predict the patterns in the data. Ripper is written in ASCI C and comes with documentation and some sample problems.

    SNePS
    Web site:
    www.cs.buffalo.edu/pub/sneps/WWW/
    FTP site: ftp.cs.buffalo.edu/pub/sneps/
    The long-term goal of The SNePS Research Group is the design and construction of a natural-language-using computerized cognitive agent, and carrying out the research in artificial intelligence, computational linguistics, and cognitive science necessary for that endeavor. The three-part focus of the group is on knowledge representation, reasoning, and natural-language understanding and generation. The group is widely known for its development of the SNePS knowledge representation/reasoning system, and Cassie, its computerized cognitive agent.

    Soar
    Web site:
    www.isi.edu/soar/soar.html
    FTP site: cs.cmu.edu/afs/cs/project/soar/public/Soar6/
    Soar has been developed to be a general cognitive architecture. We intend ultimately to enable the Soar architecture to: In other words, our intention is for Soar to support all the capabilities required of a general intelligent agent.

    TCM (Toolkit for Conceptual Modeling)
    Web site:
    www.cs.vu.nl/~tcm/
    FTP site: ftp.cs.vu.nl/pub/tcm/
    TCM (Toolkit for Conceptual Modeling) is our suite of graphical editors. TCM contains graphical editors for Entity-Relationship diagrams, Class-Relationship diagrams, Data and Event Flow diagrams, State Transition diagrams, Jackson Process Structure diagrams and System Network diagrams, Function Refinement trees and various table editors, such as a Function-Entity table editor and a Function Decomposition table editor. TCM is easy to use and performs numerous consistency checks, some of them immediately, some of them upon request.

    WEKA [New]
    Web site:
    lucy.cs.waikato.ac.nz/~ml/
    WEKA (Waikato Environment for Knowledge Analysis) is an state-of-the-art facility for applying machine learning techniques to practical problems. It is a comprehensive software "workbench" that allows people to analyse real-world data. It integrates different machine learning tools within a common framework and a uniform user interface. It is designed to support a "simplicity-first" methodology, which allows users to experiment interactively with simple machine learning tools before looking for more complex solutions.

    Connectionism

    Connectionism is a technical term for a group of related techniques. These techniques include areas such as Artificial Neural Networks, Semantic Networks and a few other similar ideas. My present focus is on neural networks (though I am looking for resources on the other techniques). Neural networks are programs designed to simulate the workings of the brain. They consist of a network of small mathematical-based nodes, which work together to form patterns of information. They have tremendous potential and currently seem to be having a great deal of success with image processing and robot control.

    Connectionist class/code libraries

    These are libraries of code or classes for use in programming within the Connectionist field. They are not meant as stand alone applications, but rather as tools for building your own applications.
    ANSI-C Neural Networks
    Web site:
    www.geocities.com/CapeCanaveral/1624/
    This site contains ANSC-C source code for 8 types of neural nets, including: They were designed to help turn the theory of a particular network model into the design for a simulator implementation , and to help with embeding an actual application into a particular network model.

    BELIEF [New]
    Web site:
    www.cs.cmu.edu/afs/cs/project/ai-repository/ai/areas/reasonng/probabl/belief/0.html
    BELIEF is a Common Lisp implementation of the Dempster and Kong fusion and propagation algorithm for Graphical Belief Function Models and the Lauritzen and Spiegelhalter algorithm for Graphical Probabilistic Models. It includes code for manipulating graphical belief models such as Bayes Nets and Relevance Diagrams (a subset of Influence Diagrams) using both belief functions and probabilities as basic representations of uncertainty. It uses the Shenoy and Shafer version of the algorithm, so one of its unique features is that it supports both probability distributions and belief functions. It also has limited support for second order models (probability distributions on parameters).

    IDEAL [New]
    Web site:
    www.rpal.rockwell.com/ideal.html

    IDEAL is a test bed for work in influence diagrams and Bayesian networks. It contains various inference algorithms for belief networks and evaluation algorithms for influence diagrams. It contains facilities for creating and editing influence diagrams and belief networks.

    IDEAL is written in pure Common Lisp and so it will run in Common Lisp on any platform. The emphasis in writing IDEAL has been on code clarity and providing high level programming abstractions. It thus is very suitable for experimental implementations which need or extend belief network technology.

    At the highest level, IDEAL can be used as a subroutine library which provides belief network inference and influence diagram evaluation as a package. The code is documented in a detailed manual and so it is also possible to work at a lower level on extensions of belief network methods.

    IDEAL comes with an optional graphic interface written in CLIM. If your Common Lisp also has CLIM, you can run the graphic interface.

    Matrix Class
    FTP site:
    pink.cs.ucla.edu/pub/
    A simple, fast, efficient C++ Matrix class designed for scientists and engineers. The Matrix class is well suited for applications with complex math algorithms. As an demonstration of the Matrix class, it was used to implement the backward error propagation algorithm for a multi-layer feed-forward artificial neural network.

    Pulcinella
    Web site:
    iridia.ulb.ac.be/pulcinella/Welcome.html
    Pulcinella is written in CommonLisp, and appears as a library of Lisp functions for creating, modifying and evaluating valuation systems. Alternatively, the user can choose to interact with Pulcinella via a graphical interface (only available in Allegro CL). Pulcinella provides primitives to build and evaluate uncertainty models according to several uncertainty calculi, including probability theory, possibility theory, and Dempster-Shafer's theory of belief functions; and the possibility theory by Zadeh, Dubois and Prade's. A User's Manual is available on request.

    S-ElimBel [New]
    Web site:
    www.spaces.uci.edu/thiery/elimbel/
    S-ElimBel is an algorithm that computes the belief in a Bayesian network, implemented in MIT-Scheme. This algorithm has the particularity of being rather easy to understand. Moreover, one can apply it to any kind of Bayesian network - it being singly connected or muliply connected. It is, however, less powerful than the standard algorithm of belief propagation. Indeed, the computation has to be reconducted entirely for each new evidence added to the network. Also, one needs to run the algorithm as many times as one has nodes for which the belief is wanted.

    Software for Flexible Bayesian Modeling [New]
    Web site:
    www.cs.utoronto.ca/~radford/fbm.software.html
    This software implements flexible Bayesian models for regression and classification applications that are based on multilayer perceptron neural networks or on Gaussian processes. The implementation uses Markov chain Monte Carlo methods. Software modules that support Markov chain sampling are included in the distribution, and may be useful in other applications.

    Spiderweb2 [New]
    Web site:
    A C++ artificial neual net library. Spiderweb2 is a complete rewrite of the original Spiderweb library, it has grown into a much more flexible and object-oriented system. The biggest change is that each neuron object is responsible for its own activations and updates, with the network providing only the scheduling aspect. This is a very powerful change, and it allows easy modification and experimentation with various network architectures and neuron types.

    There is still a lack of documentation and support for file I/O, but that will eventually get done.

    Symbolic Probabilistic Inference (SPI)
    FTP site:
    ftp.engr.orst.edu/pub/dambrosi/spi/
    Paper (ijar-94.ps): ftp.engr.orst.edu/pub/dambrosi/
    Contains Common Lisp function libraries to implement SPI type baysean nets. Documentation is very limited.
    Features:

    TresBel
    FTP site:
    iridia.ulb.ac.be/pub/hongxu/software/
    Libraries containing (Allegro) Common Lisp code for Belief Functions (aka. Dempster-Shafer evidential reasoning) as a representation of uncertainty. Very little documentation. Has a limited GUI.

    Various (C++) Neural Networks
    Web site:
    www.mcs.com/~drt/svbp.html
    Submitted by: Don Tveter
    Example neural net codes from the book, The Basis of Artificial Intelligence. These are simple example codes of these various neural nets. They work well as a good starting point for simple experimentation and for learning what the code is like behind the simulators. The types of networks available on this site are: (implemented in C++)

    Connectionist software kits/applications

    These are various applications, software kits, etc. meant for research in the field of Connectionism. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package.
    Aspirin/MIGRAINES (am6.tar.Z on ftp site)
    FTP site:
    sunsite.unc.edu/pub/academic/computer-science/neural-networks/programs/Aspirin/
    The software that we are releasing now is for creating, and evaluating, feed-forward networks such as those used with the backpropagation learning algorithm. The software is aimed both at the expert programmer/neural network researcher who may wish to tailor significant portions of the system to his/her precise needs, as well as at casual users who will wish to use the system with an absolute minimum of effort.

    JavaBayes [New]
    Web site:
    www.cs.cmu.edu/People/javabayes/index.html/
    The JavaBayes system is a set of tools, containing a graphical editor, a core inference engine and a parser. JavaBayes can produce:

    Neureka ANS (nn/xnn)
    Web site:
    www.bgif.no/neureka/
    FTP site: ftp.ii.uib.no/pub/neureka/linux/
    nn is a high-level neural network specification language. The current version is best suited for feed-forward nets, but recurrent models can and have been implemented, e.g. Hopfield nets, Jordan/Elman nets, etc. In nn, it is easy to change network dynamics. The nn compiler can generate C code or executable programs (so there must be a C compiler available), with a powerful command line interface (but everything may also be controlled via the graphical interface, xnn). It is possible for the user to write C routines that can be called from inside the nn specification, and to use the nn specification as a function that is called from a C program. Please note that no programming is necessary in order to use the network models that come with the system (`netpack').

    xnn is a graphical front end to networks generated by the nn compiler, and to the compiler itself. The xnn graphical interface is intuitive and easy to use for beginners, yet powerful, with many possibilities for visualizing network data.

    NOTE: You have to run the install program that comes with this to get the license key installed. It gets put (by default) in /usr/lib. If you (like myself) want to install the package somewhere other than in the /usr directory structure (the install program gives you this option) you will have to set up some environmental variables (NNLIBDIR & NNINCLUDEDIR are required). You can read about these (and a few other optional variables) in appendix A of the documentation (pg 113).

    PDP++
    Web site:
    www.cnbc.cmu.edu/PDP++/
    FTP site (US): cnbc.cmu.edu/pub/pdp++/
    FTP site (Europe): unix.hensa.ac.uk/mirrors/pdp++/
    As the field of Connectionist modeling has grown, so has the need for a comprehensive simulation environment for the development and testing of Connectionist models. Our goal in developing PDP++ has been to integrate several powerful software development and user interface tools into a general purpose simulation environment that is both user friendly and user extensible. The simulator is built in the C++ programming language, and incorporates a state of the art script interpreter with the full expressive power of C++. The graphical user interface is built with the Interviews toolkit, and allows full access to the data structures and processing modules out of which the simulator is built. We have constructed several useful graphical modules for easy interaction with the structure and the contents of neural networks, and we've made it possible to change and adapt many things. At the programming level, we have set things up in such a way as to make user extensions as painless as possible. The programmer creates new C++ objects, which might be new kinds of units or new kinds of processes; once compiled and linked into the simulator, these new objects can then be accessed and used like any other.

    Simple Neural Net (in Python)
    Web site:
    starship.skyport.net/crew/amk/unmaintained/
    Simple neural network code, which implements a class for 3-level networks (input, hidden, and output layers). The only learning rule implemented is simple backpropagation. No documentation (or even comments) at all, because this is simply code that I use to experiment with. Includes modules containing sample datasets from Carl G. Looney's NN book. Requires the Numeric extensions.

    SCNN
    Web site:
    apx00.physik.uni-frankfurt.de/e_ag_rt/cnn/SCNN/homepage.html
    SCNN is an universal simulating system for Cellular Neural Networks (CNN). CNN are analog processing neural networks with regular and local interconnections, governed by a set of nonlinear ordinary differential equations. Due to their local connectivity, CNN are realized as VLSI chips, which operates at very high speed.

    Semantic Networks in Python
    Web site:
    www-acs.ucsd.edu/~jstrout/python/ai/
    The semnet.py module defines several simple classes for building and using semantic networks. A semantic network is a way of representing knowledge, and it enables the program to do simple reasoning with very little effort on the part of the programmer.

    The following classes are defined:

    With these three object types, you can very quickly define knowledge about a set of objects, and query them for logical conclusions.

    SNNS
    Web site:
    www.informatik.uni-stuttgart.de/ipvr/bv/projekte/snns/snns.html
    FTP site: ftp.informatik.uni-stuttgart.de/pub/SNNS/
    Stuttgart Neural Net Simulator (version 4.1). An awesome neural net simulator. Better than any commercial simulator I've seen. The simulator kernel is written in C (it's fast!). It supports over 20 different network architectures, has 2D and 3D X-based graphical representations, the 2D GUI has an integrated network editor, and can generate a separate NN program in C.
    SNNS is very powerful, though a bit difficult to learn at first. To help with this it comes with example networks and tutorials for many of the architectures.
    ENZO, a supplementary system allows you to evolve your networks with genetic algorithms.

    The Readme.linux file that comes with this package must be old. It's instructions for building the package are wrong. I've edited it to reflect what I had to do to get the package to compile. Please download SNNS.Readme.linux and use it instead of the Readme.linux file that comes with the distribution.

    SPRLIB/ANNLIB
    Web site:
    www.ph.tn.tudelft.nl/~sprlib/
    SPRLIB (Statistical Pattern Recognition Library) was developed to support the easy construction and simulation of pattern classifiers. It consist of a library of functions (written in C) that can be called from your own program. Most of the well-known classifiers are present (k-nn, Fisher, Parzen, ....), as well as error estimation and dataset generation routines.

    ANNLIB (Artificial Neural Networks Library) is a neural network simulation library based on the data architecture laid down by SPRLIB. The library contains numerous functions for creating, training and testing feed-forward networks. Training algorithms include back-propagation, pseudo-Newton, Levenberg-Marquardt, conjugate gradient descent, BFGS.... Furthermore, it is possible - due to the datastructures' general applicability - to build Kohonen maps and other more exotic network architectures using the same data types.

    Evolutionary Computing

    Evolutionary computing is actually a broad term for a vast array of programming techniques, including genetic algorithms, complex adaptive systems, evolutionary programming, etc. The main thrust of all these techniques is the idea of evolution. The idea that a program can be written that will evolve toward a certain goal. This goal can be anything from solving some engineering problem to winning a game.

    EC class/code libraries

    These are libraries of code or classes for use in programming within the evolutionary computation field. They are not meant as stand alone applications, but rather as tools for building your own applications.
    FORTRAN GA
    Web site:
    www.staff.uiuc.edu/~carroll/ga.html
    This program is a FORTRAN version of a genetic algorithm driver. This code initializes a random sample of individuals with different parameters to be optimized using the genetic algorithm approach, i.e. evolution via survival of the fittest. The selection scheme used is tournament selection with a shuffling technique for choosing random pairs for mating. The routine includes binary coding for the individuals, jump mutation, creep mutation, and the option for single-point or uniform crossover. Niching (sharing) and an option for the number of children per pair of parents has been added. More recently, an option for the use of a micro-GA has been added.

    GAGS
    Web site:
    kal-el.ugr.es/gags.html
    FTP site: kal-el.ugr.es/GAGS/
    Genetic Algorithm application generator and class library written mainly in C++.
    As a class library, and among other thing, GAGS includes: As an application generator (written in PERL), you only need to supply it with an ANSI-C or C++ fitness function, and it creates a C++ program that uses the above library to 90% capacity, compiles it, and runs it, saving results and presenting fitness thru gnuplot.

    GAlib: Matthew's Genetic Algorithms Library
    Web Site:
    lancet.mit.edu/ga/
    FTP site: lancet.mit.edu/pub/ga/
    Register GAlib at: http://lancet.mit.edu/ga/Register.html
    GAlib contains a set of C++ genetic algorithm objects. The library includes tools for using genetic algorithms to do optimization in any C++ program using any representation and genetic operators. The documentation includes an extensive overview of how to implement a genetic algorithm as well as examples illustrating customizations to the GAlib classes.

    GALOPPS
    Web site:
    GARAGe.cps.msu.edu/software/software-index.html
    FTP site: garage.cps.msu.edu/pub/GA/galopps/
    GALOPPS is a flexible, generic GA, in 'C'. It was based upon Goldberg's Simple Genetic Algorithm (SGA) architecture, in order to make it easier for users to learn to use and extend.

    GALOPPS extends the SGA capabilities several fold:

    GAS [New]
    Web site:
    starship.skyport.net/crew/gandalf
    FTP site: ftp.coe.uga.edu/users/jae/ai
    GAS means "Genetic Algorithms Stuff". GAS is freeware.
    Purpose of GAS is to explore and exploit artificial evolutions. Primary implementation language of GAS is Python. The GAS software package is meant to be a Python framework for applying genetic algorithms. It contains an example application where it is tried to breed Python program strings. This special problem falls into the category of Genetic Programming (GP), and/or Automatic Programming. Nevertheless, GAS tries to be useful for other applications of Genetic Algorithms as well.

    GECO
    FTP site:
    ftp://ftp.aic.nrl.navy.mil/pub/galist/src/
    GECO (Genetic Evolution through Combination of Objects), an extendible object-oriented tool-box for constructing genetic algorithms (in Lisp). It provides a set of extensible classes and methods designed for generality. Some simple examples are also provided to illustrate the intended use.

    GPdata
    FTP site: ftp.cs.bham.ac.uk/pub/authors/W.B.Langdon/gp-code/
    Documentation (GPdata-icga-95.ps): cs.ucl.ac.uk/genetic/papers/
    GPdata-3.0.tar.gz (C++) contains a version of Andy Singleton's GP-Quick version 2.1 which has been extensively altered to support: This ftp site also contains a small C++ program (ntrees.cc) to calculate the number of different there are of a given length and given function and terminal set.

    gpjpp Genetic Programming in Java
    Web site:
    www.turbopower.com/~kimk/gpjpp.asp
    gpjpp is a Java package I wrote for doing research in genetic programming. It is a port of the gpc++ kernel written by Adam Fraser and Thomas Weinbrenner. Included in the package are four of Koza's standard examples: the artificial ant, the hopping lawnmower, symbolic regression, and the boolean multiplexer. Here is a partial list of its features:

    GP Kernel
    Web site:
    www.emk.e-technik.th-darmstadt.de/~thomasw/gp.html
    The GP kernel is a C++ class library that can be used to apply genetic programming techniques to all kinds of problems. The library defines a class hierarchy. An integral component is the ability to produce automatically defined functions as found in Koza's "Genetic Programming II".Technical documentation (postscript format) is included. There is also a short introduction into genetic programming.

    Functionality includes; Automatically defined functions (ADFs), tournament and fitness proportionate selection, demetic grouping, optional steady state genetic programming kernel, subtree crossover, swap and shrink mutation, a way of changing every parameter of the system without recompilation, capacity for multiple populations, loading and saving of populations and genetic programs, standard random number generator, internal parameter checks.

    lil-gp
    Web site:
    isl.msu.edu/GA/software/lil-gp/index.html
    FTP site: isl.cps.msu.edu/pub/GA/lilgp/
    patched lil-gp * [New]
    Web site:
    www.cs.umd.edu/users/seanl/patched-gp
    lil-gp is a generic 'C' genetic programming tool. It was written with a number of goals in mind: speed, ease of use and support for a number of options including: * The patched lil-gp kernel is strongly-typed, with modifications on multithreading, fixes to some *serious* bugs in lilgp, coevolution, and other tweaks and features.

    PGAPack Parallel Genetic Algorithm Library
    Web site:
    www.mcs.anl.gov/home/levine/PGAPACK/index.html
    FTP site: ftp.mcs.anl.gov/pub/pgapack/
    PGAPack is a general-purpose, data-structure-neutral, parallel genetic algorithm library. It is intended to provide most capabilities desired in a genetic algorithm library, in an integrated, seamless, and portable manner. Key features are in PGAPack V1.0 include:

    Sugal
    Web site:
    www.trajan-software.demon.co.uk/sugal.htm
    Sugal [soo-gall] is the SUnderland Genetic ALgorithm system. The aim of Sugal is to support research and implementation in Genetic Algorithms on a common software platform. As such, Sugal supports a large number of variants of Genetic Algorithms, and has extensive features to support customization and extension.

    EC software kits/applications

    These are various applications, software kits, etc. meant for research in the field of evolutionary computing. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package.
    ADATE(Automatic Design of Algorithms Through Evolution)
    Web site:
    www-ia.hiof.no/~rolando/adate_intro.html
    ADATE is a system for automatic programming i.e., inductive inference of algorithms, which may be the best way to develop artificial and general intelligence.

    The ADATE system can automatically generate non-trivial and novel algorithms. Algorithms are generated through large scale combinatorial search that employs sophisticated program transformations and heuristics. The ADATE system is particularly good at synthesizing symbolic, functional programs and has several unique qualities.

    esep & xesep [New]
    Web site(esep):
    www.iit.edu/~linjinl/esep.html Web site(xesep): www.iit.edu/~linjinl/xesep.html
    This is a new scheduler, called Evolution Scheduler, based on Genetic Algorithms and Evolutionary Programming. It lives with original Linux priority scheduler.This means you don't have to reboot to change the scheduling policy. You may simply use the manager program esep to switch between them at any time, and esep itself is an all-in-one for scheduling status, commands, and administration. We didn't intend to remove the original priority scheduler; instead, at least, esep provides you with another choice to use a more intelligent scheduler, which carries out natural competition in an easy and effective way.

    Xesep is a graphical user interface to the esep (Evolution Scheduling and Evolving Processes). It's intended to show users how to start, play, and feel the Evolution Scheduling and Evolving Processes, including sub-programs to display system status, evolving process status, queue status, and evolution scheduling status periodically in as small as one mini-second.

    FSM-Evolver [New]
    Web site:
    pages.prodigy.net/czarneckid
    A Java (jdk-v1.0.2+) code library that is used to evolve finite state machines. The problem included in the package is the Artificial Ant problem. You should be able to compile the .java files and then run: java ArtificialAnt.

    GPsys [New]
    Web site:
    www.cs.ucl.ac.uk/staff/A.Qureshi/gpsys.html
    GPsys (pronounced gipsys) is a Java (requires Java 1.1 or later) based Genetic Programming system developed by Adil Qureshi. The software includes documentation, source and executables.

    Feature Summary:

    Alife

    Alife takes yet another approach to exploring the mysteries of intelligence. It has many aspects similar to EC and Connectionism, but takes these ideas and gives them a meta-level twist. Alife emphasizes the development of intelligence through emergent behavior of complex adaptive systems. Alife stresses the social or group based aspects of intelligence. It seeks to understand life and survival. By studying the behaviors of groups of 'beings' Alife seeks to discover the way intelligence or higher order activity emerges from seemingly simple individuals. Cellular Automata and Conway's Game of Life are probably the most commonly known applications of this field.

    Alife class/code libraries

    These are libraries of code or classes for use in programming within the artificial life field. They are not meant as stand alone applications, but rather as tools for building your own applications.

    John von Neumann Universal Constructor
    Web site:
    alife.santafe.edu/alife/software/jvn.html
    FTP site: alife.santafe.edu/pub/SOFTWARE/jvn/
    The universal constructor of John von Neumann is an extension of the logical concept of universal computing machine. In the cellular environment proposed by von Neumann both computing and constructive universality can be achieved. Von Neumann proved that in his cellular lattice both a Turing machine and a machine capable of producing any other cell assembly, when fed with a suitable program, can be embedded. He called the latter machine a "universal constructor" and showed that, when provided with a program containing its own description, this is capable of self-reproducing.

    Swarm
    Web site:
    www.santafe.edu/projects/swarm
    FTP site: ftp.santafe.edu/pub/swarm
    The swarm Alife simulation kit. Swarm is a simulation environment which facilitates development and experimentation with simulations involving a large number of agents behaving and interacting within a dynamic environment. It consists of a collection of classes and libraries written in Objective-C and allows great flexibility in creating simulations and analyzing their results. It comes with three demos and good documentation.

    Swarm 1.0 is out. It requires libtclobjc and BLT 2.1 (both available at the swarm site).

    Alife software kits, applications, etc.

    These are various applications, software kits, etc. meant for research in the field of artificial life. Their ease of use will vary, as they were designed to meet some particular research interest more than as an easy to use commercial package.
    BugsX
    FTP site:
    ftp.Germany.EU.net/pub/research/softcomp/Alife/packages/bugsx/
    Display and evolve biomorphs. It is a program which draws the biomorphs based on parametric plots of Fourier sine and cosine series and let's you play with them using the genetic algorithm.

    The Cellular Automata Simulation System
    Web site:
    www.cs.runet.edu/~dana/ca/cellular.html
    The system consists of a compiler for the Cellang cellular automata programming language, along with the corresponding documentation, viewer, and various tools. Cellang has been undergoing refinement for the last several years (1991-1995), with corresponding upgrades to the compiler. Postscript versions of the tutorial and language reference manual are available for those wanting more detailed information. The most important distinguishing features of Cellang, include support for:

    dblife & dblifelib
    FTP site:
    ftp.cc.gatech.edu/ac121/linux/games/amusements/life/
    dblife: Sources for a fancy Game of Life program for X11 (and curses). It is not meant to be incredibly fast (use xlife for that:-). But it IS meant to allow the easy editing and viewing of Life objects and has some powerful features. The related dblifelib package is a library of Life objects to use with the program.

    dblifelib: This is a library of interesting Life objects, including oscillators, spaceships, puffers, and other weird things. The related dblife package contains a Life program which can read the objects in the Library.

    Drone
    Web site:
    pscs.physics.lsa.umich.edu/Software/Drone/
    Drone is a tool for automatically running batch jobs of a simulation program. It allows sweeps over arbitrary sets of parameters, as well as multiple runs for each parameter set, with a separate random seed for each run. The runs may be executed either on a single computer or over the Internet on a set of remote hosts. Drone is written in Expect (an extension to the Tcl scripting language) and runs under Unix. It was originally designed for use with the Swarm agent-based simulation framework, but Drone can be used with any simulation program that reads parameters from the command line or from an input file.

    EcoLab [New]
    Web site:
    parallel.acsu.unsw.edu.au/rks/ecolab.html
    EcoLab is a system that implements an abstract ecology model. It is written as a set of Tcl/Tk commands so that the model parameters can easily be changed on the fly by means of editing a script. The model itself is written in C++.

    Game Of Life (GOL) [New]
    Web site:
    www.arrakeen.demon.co.uk/downloads.html
    FTP site: sunsite.unc.edu/pub/Linux/science/ai/life
    GOL is a simulator for conway's game of life (a simple cellular automata), and other simple rule sets. The emphasis here is on speed and scale, in other words you can setup large and fast simulations.

    LEE
    Web site:
    www-cse.ucsd.edu/users/fil/lee/lee.html
    FTP site: cs.ucsd.edu/pub/LEE/
    LEE (Latent Energy Environments) is both an Alife model and a software tool to be used for simulations within the framework of that model. We hope that LEE will help understand a broad range of issues in theoretical, behavioral, and evolutionary biology. The LEE tool described here consists of approximately 7,000 lines of C code and runs in both Unix and Macintosh platforms.

    Net-Life & ZooLife
    Web site:
    www.geocities.com/SiliconValley/Heights/1051**
    FTP site: ftp.coe.uga.edu/users/jae/alife/
    *(netlife-2.0.tar.gz contains both Net-Life and ZooLife)
    Net-Life is a simulation of artificial-life, with neural "brains" generated via slightly random techniques. Net-Life uses artificial neural nets and evolutionary algorithms to breed artificial organisms that are similar to single cell organisms. Net-life uses asexual reproduction of its fittest individuals with a chance of mutation after each round to eventually evolve successful life-forms.

    ZooLife is a simulation of artificial-life. ZooLife uses probabilistic methods and evolutionary algorithms to breed artificial organisms that are similar to plant/animal zoo organisms. ZooLife uses asexual reproduction with a chance of mutation.

    Primordial Soup
    Web site:
    alife.santafe.edu/alife/software/psoup.html
    Primordial Soup is an artificial life program. Organisms in the form of computer software loops live in a shared memory space (the "soup") and self-reproduce. The organisms mutate and evolve, behaving in accordance with the principles of Darwinian evolution.

    The program may be started with one or more organisms seeding the soup. Alternatively, the system may be started "sterile", with no organisms present. Spontaneous generation of self-reproducing organisms has been observed after runs as short as 15 minutes.

    Tierra
    Web site:
    www.hip.atr.co.jp/~ray/tierra/tierra.html
    FTP site: alife.santafe.edu/pub/SOFTWARE/Tierra/
    Alternate FTP site: ftp.cc.gatech.edu/ac121/linux/science/biology/
    Tierra's written in the C programming language. This source code creates a virtual computer and its operating system, whose architecture has been designed in such a way that the executable machine codes are evolvable. This means that the machine code can be mutated (by flipping bits at random) or recombined (by swapping segments of code between algorithms), and the resulting code remains functional enough of the time for natural (or presumably artificial) selection to be able to improve the code over time.

    TIN
    FTP site:
    ftp.coe.uga.edu/users/jae/alife/
    This program simulates primitive life-forms, equipped with some basic instincts and abilities, in a 2D environment consisting of cells. By mutation new generations can prove their success, and thus passing on "good family values".

    The brain of a TIN can be seen as a collection of processes, each representing drives or impulses to behave a certain way, depending on the state/perception of the environment ( e.g. presence of food, walls, neighbors, scent traces) These behavior process currently are : eating, moving, mating, relaxing, tracing others, gathering food and killing. The process with the highest impulse value takes control, or in other words: the tin will act according to its most urgent need.

    XLIFE
    FTP site:
    ftp.cc.gatech.edu/ac121/linux/games/amusements/life/
    This program will evolve patterns for John Horton Conway's game of Life. It will also handle general cellular automata with the orthogonal neighborhood and up to 8 states (it's possible to recompile for more states, but very expensive in memory). Transition rules and sample patterns are provided for the 8-state automaton of E. F. Codd, the Wireworld automaton, and a whole class of `Prisoner's Dilemma' games.

    Autonomous Agents

    Also known as intelligent software agents or just agents, this area of AI research deals with simple applications of small programs that aid the user in his/her work. They can be mobile (able to stop their execution on one machine and resume it on another) or static (live in one machine). They are usually specific to the task (and therefore fairly simple) and meant to help the user much as an assistant would. The most popular (ie. widely known) use of this type of application to date are the web robots that many of the indexing engines (eg. webcrawler) use.

    AgentK
    FTP site:
    ftp.csd.abdn.ac.uk/pub/wdavies/agentk
    This package synthesizes two well-known agent paradigms: Agent-Oriented Programming, Shoham (1990), and the Knowledge Query & Manipulation Language, Finin (1993). The initial implementation of AOP, Agent-0, is a simple language for specifying agent behaviour. KQML provides a standard language for inter-agent communication. Our integration (which we have called Agent-K) demonstrates that Agent-0 and KQML are highly compatible. Agent-K provides the possibility of inter-operable (or open) software agents, that can communicate via KQML and which are programmed using the AOP approach.

    Agent, the Perl5 Module
    FTP site:
    ftp.hawk.igs.net/pub/users/jduncan/modules/Agent/
    The Agent is a prototype for an Information Agent system. It is both platform and language independent, as it stores contained information in simple packed strings. It can be packed and shipped across any network with any format, as it freezes itself in its current state.

    AGENT TCL
    Web site:
    www.cs.dartmouth.edu/~agent/
    FTP site: ftp.cs.dartmouth.edu/pub/agents/
    A transportable agent is a program that can migrate from machine to machine in a heterogeneous network. The program chooses when and where to migrate. It can suspend its execution at an arbitrary point, transport to another machine and resume execution on the new machine. For example, an agent carrying a mail message migrates first to a router and then to the recipient's mailbox. The agent can perform arbitrarily complex processing at each machine in order to ensure that the message reaches the intended recipient.

    Aglets Workbench
    Web site:
    www.trl.ibm.co.jp/aglets/
    An aglet is a Java object that can move from one host on the Internet to another. That is, an aglet that executes on one host can suddenly halt execution, dispatch to a remote host, and resume execution there. When the aglet moves, it takes along its program code as well as its state (data). A built-in security mechanism makes it safe for a computer to host untrusted aglets. The Java Aglet API (J-AAPI) is a proposed public standard for interfacing aglets and their environment. J-AAPI contains methods for initializing an aglet, message handling, and dispatching, retracting, deactivating/activating, cloning, and disposing of the aglet. J-AAPI is simple, flexible, and stable. Application developers can write platform-independent aglets and expect them to run on any host that supports J-AAPI.

    Ara
    Web site:
    www.uni-kl.de/AG-Nehmer/Ara/
    Ara is a platform for the portable and secure execution of mobile agents in heterogeneous networks. Mobile agents in this sense are programs with the ability to change their host machine during execution while preserving their internal state. This enables them to handle interactions locally which otherwise had to be performed remotely. Ara's specific aim in comparison to similar platforms is to provide full mobile agent functionality while retaining as much as possible of established programming models and languages.

    JAFMAS [New]
    Web site:
    www.ececs.uc.edu/~abaker/JAFMAS
    JAFMAS provides a framework to guide the coherent development of multiagent systems along with a set of classes for agent deployment in Java. The framework is intended to help beginning and expert developers structure their ideas into concrete agent applications. It directs development from a speech-act perspective and supports multicast and directed communication, KQML or other speech-act performatives and analysis of multiagent system coherency and consistency.

    Only four of the provided Java classes must be extended for any application. Provided examples of the N-Queens and Supply Chain Integration use only 567 and 1276 lines of additional code respectively for implementation.

    JATLite
    Web site:
    java.stanford.edu/java_agent/html/
    JATLite is providing a set of java packages which makes easy to build multi-agent systems using Java. JATLite provides only light-weight, small set of packages so that the developers can handle all the packages with little efforts. For flexibility JATLite provides four different layers from abstract to Router implementation. A user can access any layer we are providing. Each layer has a different set of assumptions. The user can choose an appropriate layer according to the assumptions on the layer and user's application. The introduction page contains JATLite features and the set of assumptions for each layer.

    Java(tm) Agent Template
    Web site:
    cdr.stanford.edu/ABE/JavaAgent.html
    The JAT provides a fully functional template, written entirely in the Java language, for constructing software agents which communicate peer-to-peer with a community of other agents distributed over the Internet. Although portions of the code which define each agent are portable, JAT agents are not migratory but rather have a static existence on a single host. This behavior is in contrast to many other "agent" technologies. (However, using the Java RMI, JAT agents could dynamically migrate to a foreign host via an agent resident on that host). Currently, all agent messages use KQML as a top-level protocol or message wrapper. The JAT includes functionality for dynamically exchanging "Resources", which can include Java classes (e.g. new languages and interpreters, remote services, etc.), data files and information inlined into the KQML messages.

    Java-To-Go
    Web site:
    ptolemy.eecs.berkeley.edu/dgm/javatools/java-to-go/
    Java-To-Go is an experimental infrastructure that assists in the development and experimentation of mobile agents and agent-based applications for itinerative computing (itinerative computing: the set of applications that requires site-to-site computations. The main emphasis here is on a easy-to-setup environment that promotes quick experimentation on mobile agents.

    Kafka [New]
    Web site:
    www.fujitsu.co.jp/hypertext/free/kafka/
    Kafka is yet another agent library designed for constructing multi-agent based distributed applications. Kafka is a flexible, extendable, and easy-to-use java class library for programmers who are familiar with distributed programming. It is based on Java's RMI and has the following added features:
    Runtime Reflection:
    Agents can modify their behaviour (program codes) at runtime. The behaviour of the agent is represented by an abstract class Action. It is useful for remote maintenance or installation services.
    Remote Evaluation:
    Agents can receive and evaluate program codes (classes) with or without the serialized object. Remote evaluation is a fundamental function of a mobile agent and is thought to be a push model of service delivery.
    Distributed Name Service:
    Agents have any number of logical names that don't contain the host name. These names can be managed by the distributed directories.
    Customizable security policy
    a very flexible, customizable, 3-layered security model is implemented in Kafka.
    100% Java and RMI compatible:
    Kafka is written completely in Java. Agent is a Java RMI server object itself. So, agents can directly communicate with other RMI objects.

    Khepera Simulator
    Web site:
    diwww.epfl.ch/lami/team/michel/khep-sim/
    Khepera Simulator is a public domain software package written by Olivier MICHEL during the preparation of his Ph.D. thesis, at the Laboratoire I3S, URA 1376 of CNRS and University of Nice-Sophia Antipolis, France. It allows to write your own controller for the mobile robot Khepera using C or C++ languages, to test them in a simulated environment and features a nice colorful X11 graphical interface. Moreover, if you own a Khepera robot, it can drive the real robot using the same control algorithm. It is mainly oriented toward to researchers studying autonomous agents.

    Mole
    Web site:
    www.informatik.uni-stuttgart.de/ipvr/vs/projekte/mole.html
    Mole is an agent system supporting mobile agents programmed in Java. Mole's agents consist of a cluster of objects, which have no references to the outside, and as a whole work on tasks given by the user or another agent. They have the ability to roam a network of "locations" autonomously. These "locations" are an abstraction of real, existing nodes in the underlying network. They can use location-specific resources by communicating with dedicated agents representing these services. Agents are able to use services provided by other agents and to provide services as well.

    Odyssey
    Web site:
    www.genmagic.com/agents/
    Odyssey is General Magic's initial implementation of mobile agents in 100% pure Java. The Odyssey class libraries enable you to develop your own mobile agent applications. Use mobile agents to access data, make decisions and notify users. Your agent-enabled applications may also take full advantage of the Java platform and use other third party libraries, for example, to access remote CORBA objects or to access relational databases using JDBC. To see how it's done, take a look at the sample applications included as part of the Odyssey download.

    Penguin!

    FTP site:
    www.perl.org/CPAN/modules/by-category/23_Miscellaneous_Modules/Penguin/FSG/
    Penguin is a Perl 5 module. It provides you with a set of functions which allow you to: The combination of these functions enable direct Perl coding of algorithms to handle safe internet commerce, mobile information-gathering agents, "live content" web browser helper apps, distributed load-balanced computation, remote software update, distance machine administration, content-based information propagation, Internet-wide shared-data applications, network application builders, and so on.

    SimRobot
    Web site:
    www.informatik.uni-bremen.de/~simrobot/
    FTP site: ftp.uni-bremen.de/pub/ZKW/INFORM/simrobot/
    SimRobot is a program for simulation of sensor based robots in a 3D environment. It is written in C++, runs under UNIX and X11 and needs the graphics toolkit XView.

    TclRobots
    FTP site:
    ftp.neosoft.com/pub/tcl/sorted/games/tclrobots-2.0/
    Redhat Patch: ftp.coe.uga.edu/users/jae/ai/tclrobots-redhat.patch
    RPMs: ftp://ftp.redhat.com/contrib/
    TclRobots is a programming game, similar to 'Core War'. To play TclRobots, you must write a Tcl program that controls a robot. The robot's mission is to survive a battle with other robots. Two, three, or four robots compete during a battle, each running different programs (or possibly the same program in different robots.) Each robot is equipped with a scanner, cannon, drive mechanism. A single match continues until one robot is left running. Robots may compete individually, or combine in a team oriented battle. A tournament can be run with any number of robot programs, each robot playing every other in a round-robin fashion, one-on-one. A battle simulator is available to help debug robot programs.

    The TclRobots program provides a physical environment, imposing certain game parameters to which all robots must adhere. TclRobots also provides a view on a battle, and a controlling user interface. TclRobots requirements: a wish interpreter built from Tcl 7.4 and Tk 4.0.

    The Tocoma Project
    Web site:
    www.cs.uit.no/DOS/Tacoma/index.html
    An agent is a process that may migrate through a computer network in order to satisfy requests made by clients. Agents are an attractive way to describe network-wide computations.

    The TACOMA project focuses on operating system support for agents and how agents can be used to solve problems traditionally addressed by operating systems. We have implemented a series of prototype systems to support agents.

    TACOMA Version 1.2 is based on UNIX and TCP. The system supports agents written in C, Tcl/Tk, Perl, Python, and Scheme (Elk). It is implemented in C. This TACOMA version has been in public domain since April 1996.

    We are currently focusing on heterogeneity, fault-tolerance, security and management issues. Also, several TACOMA applications are under construction. We implemented StormCast 4.0, a wide-area network weather monitoring system accessible over the internet, using TACOMA and Java. We are now in the process of evaluating this application, and plan to build a new StormCast version to be completed by June 1997.

    Virtual Secretary Project (ViSe) (Tcl/Tk) [New]
    Web site:
    www.cs.uit.no/DOS/Virt_Sec
    The motivation of the Virtual Secretary project is to construct user-model-based intelligent software agents, which could in most cases replace human for secretarial tasks, based on modern mobile computing and computer network. The project includes two different phases: the first phase (ViSe1) focuses on information filtering and process migration, its goal is to create a secure environment for software agents using the concept of user models; the second phase (ViSe2) concentrates on agents' intelligent and efficient cooperation in a distributed environment, its goal is to construct cooperative agents for achieving high intelligence. (Implemented in Tcl/TclX/Tix/Tk)

    VWORLD
    Web site:
    www.ai.uga.edu/~jae/projects.html#vworld
    Vworld is a simulated environment for research with autonomous agents written in prolog. It is currently in something of an beta stage. It works well with SWI-prolog, but should work with Quitnus-prolog with only a few changes. It is being designed to serve as an educational tool for class projects dealing with prolog and autonomous agents. It comes with three demo worlds or environments, along with sample agents for them.
    There are two versions now. One written for SWI-prolog and one written for LPA-prolog. Documentation is roughly done (with a student/professor framework in mind), and a graphical interface is planned.

    WebMate
    Web site:
    www.cs.cmu.edu/~softagents/webmate/
    WebMate is a personal agent for World-Wide Web browsing and searching. It accompanies you when you travel on the internet and provides you what you want.
    Features include:

    AI & Alife related newsgroups

    These newsgroups are not Linux specific. But they are good resources for anyone working in artificial intelligence or artificial life. If you can't access these newsgroups, many of their FAQs are available at:
    http://www.cis.ohio-state.edu/hypertext/faq/bngusenet/comp/ai/top.html

    AI & Alife resource links

    These are a few of the many AI and Alife sites out there. These sites are good places to start hunting for more information or for finding software. I'll be adding more links to this list soon, as well as organizing it better. These links are not Linux specific, but I wanted to include them to provide a jump off point to the huge amount of info related to these topics located on the web.

    AI/Alife Archives, Research, Bibliographies, etc.

    All Catagories
  • SAL.KachinaTech.COM/Z/3/-Scientific Applications for Linux's AI page
  • www.cs.cmu.edu/Web/Groups/AI/html/repository.html-CMU Artificial Intelligence Repository
  • liinwww.ira.uka.de/bibliography/Ai/index.html -Bibliographies on Artificial Intelligence [New]
  • Traditional AI
  • www.mcs.net/~jorn/html/ai.html-Outsider's Guide to AI
  • www.cs.cmu.edu/afs/cs.cmu.edu/project/ai-repository/ai/html/cltl/clm/clm.html-Common Lisp Book
  • www.elwoodcorp.com/alu/table/contents.htm-The Association of Lisp Users
  • www.cs.indiana.edu/scheme-repository/home.html-Scheme repository
  • www.aic.nrl.navy.mil/-Navy Center for Applied Research in Artificial Intelligence
  • intranet.ca/~sshah/waste/waste.html-WASTE (AI Contest)
  • www.cs.washington.edu/research/jair/home.html-Journal of Artificial Intelligence Research
  • www.cs.ucl.ac.uk/misc/ai/-University of London's AI Resource Page
  • www.cris.com/~swoodcoc/ai.html -Artificial Intelligence in Games
  • strips.lboro.ac.uk/bib/ -An Online Bibliography on Planning and Scheduling
  • Connectionism
  • www.neuronet.ph.kcl.ac.uk/neuronet/software/software.html-NEuroNet - ANN software
  • Evolutionary Computing
  • ftp://ftp.mad-scientist.com/pub/genetic-programming/-John Koza's Genetic Programming archive.
  • www.cpsc.ucalgary.ca/~jacob/Evolvica/ -Tutorial: Evolutionary Algorithms in Action
  • alife.santafe.edu/~joke/encore/-ENCORE-The Hitch-Hikers Guide to Evolutionary Computation
  • gal4.ge.uiuc.edu/illigal.home.html-IlliGAL Home Page (GA's)
  • isl.msu.edu/GA/-MSU GARAGe Home Page (GA's)
  • www.aracnet.com/~wwir/NovaGenetica/-Nova Genetica (GA's)
  • Artifical Life
  • alife.santafe.edu/~joke/zooland/-ZooLand Artificial Life Resources
  • alife.santafe.edu-Santafe's Alife page
  • www.krl.caltech.edu/~brown/alife/-Alife FAQ
  • www.cogs.susx.ac.uk/users/ezequiel/alife-page/alife.html-ALife Bibliography
  • complex.csu.edu.au/complex/-Complex Systems Information Network
  • www.geneticprogramming.com/-The Genetic Programming Notebook
  • gracco.irmkant.rm.cnr.it/luigi/lupa_algames.html-The Artificial Life Games Homepage
  • www.krl.caltech.edu/~charles/alife-game/-Project: Von Neumann
  • Agents & Bots
  • agents.www.media.mit.edu/groups/agents/-MIT Media Lab, Autonomous Agents Group
  • www.cs.umbc.edu/agents/agentnews/-AgentNews Webletter
  • www.cs.umbc.edu/agents-UMBC AgentWeb (includes KQML info) [New]
  • www.agent.org-Agent Society Home Page
  • www.botspot.com/main.html-The BotSpot (a software agent resource page) [New]
  • www.cselt.it/fipa/-FIPA Foundation for Intelligent Physical Agents
  • www.robotmag.com/-Robot Magazine
  • www.geocities.com/SiliconValley/3086/robots/index2.htm-Intro to Indexing Bots (aka spiders) [New]
  • luz.cs.nmt.edu/~rtlinux-Real time linux (for robotics, etc)