Open Source Java Artificial Intelligence Software

OpenKM is a electronic document management system and record management system EDRMS ( DMS, RMS, CMS ). It provides modern and flexible architecture that meet today's IT demands, based on open technology (Java, Tomcat, GWT, Lucene, Hibernate, Spring and jBPM), powerful and scalable multiplatform application. OpenKM is a Web 2.0 application that works with Internet Explorer, Firefox, Safari and Opera. Can be configured in major DMBS like Oracle, PostgreSQL and MySQL among others. Due to its technological architecture design, OpenKM meets the document management needs of businesses of all sizes (from SMEs to big corporations). Thanks to its elegant and intuitive interface, OpenKM transforms complex operations into easy tasks. The most relevant functions of OpenKM is the indexing of the most common types of files: text, Office, Office 2007, OpenOffice, PDF, HTML, XML, MP3, JPEG, etc. For a complete feature list take a look at http://goo.gl/au8cQy

CLIPS is a forward-chaining rule-based programming language written in C that also provides procedural and object-oriented programming facilities.

Open source JDBC 3.0 type 4 driver for Microsoft SQL Server (6.5 up to 2012) and Sybase ASE. jTDS is a complete implementation of the JDBC 3.0 spec and the fastest JDBC driver for MS SQL Server. For more information see http://jtds.sourceforge.net/

Clustering Variation looks for a good subset of attributes in order to improve the classification accuracy of supervised learning techniques in classification problems with a huge number of attributes involved. It first creates a ranking of attributes based on the Variation value, then divide into two groups, last using Verification method to select the best group.

XiangQi Wizard (Chinese Chess Wizard) is a powerful XiangQi (chinese chess) program, which supports UCCI engines. XQWizard Light is the Mobile version for Windows CE and Java ME. ElephantEye is the UCCI engine in XQWizard with strong AI.

Software for the competitions on computational intelligence in games.

Marvin is an image processing framework that provides features for image and video frame manipulation, multithreading image processing, image filtering and analysis, unit testing, performance analysis and addition of new features via plug-in.

VLE is a multi-modeling and simulation environment to study complex dynamic systems. VLE is based on the discrete event specification DEVS. and it implements the DSDE formalism (A merge of Dynamic Structure DEVS, DSDEVS, with Parallel DEVS, PDEVS). VLE provides a complete set of C++ libraries, called VFL (VLE Foundation Libraries), to develop DEVS models, to gets results of simulations, to launch simulation on cluster. The models can be developed with the DEVS formalism or with the classical mathematical formalism: Ordinary Differential Equation with Euler, Range-Kutta or QSS integrator, Finite state automaton (FDDEVS, UML State chart, Hybrid Petri net). The VLE environment provides an IDE to develop C++ models, DEVS coupled models. VLE have also three ports to use the VFL with Python, Java and R programming languages.

Panzer Combat II is a multi-player voice and webcam enabled computer-assisted distributed miniature wargame of World War II tank combat. Firing is done by placing a webcam behind the aiming unit. Distance to target is computed using computer vision. Action inside the tanks is performed on the computer screen while battlefield strategy is played on the miniature terrain. Both camps can use a different laptop or tablet, the game will interconnect. You can try it online : http://server.panzercombat.com/PCII_Web/move.htm Look at battle reports : http://www.flickr.com/photos/panzercombatii Or watch a demo : http://www.youtube.com/watch?v=WcjfV8Odtss 100% CLEAN : http://games.softpedia.com/progClean/Panzer-Combat-II-Clean-95530.html

Weka genetic algorithm filter plugin to generate synthetic instances. This Weka Plugin implementation uses a Genetic Algorithm to create new synthetic instances to solve the imbalanced dataset problem. See my master thesis available for download, for further details.

HSSVM(Hyper-Sphere Support Vector Machines) is a software for solving multi-classification problem, implemented by Java.

"Java Artificial Intelligence Markup Language PAD" is a tool that manages ProgramD AI (on local or remote machines) and AIML files with real-time previews and it provides a network support to test AI capabilities over many network protocols.

Java version of the game "Color Expansion". The main purpose is to develop a strong AI to compete against other AIs and to be fun and challenging for human players to play against.

This project has been moved to bitbucket.org: - https://bitbucket.org/vahidi/jbdd/wiki/Home - https://bitbucket.org/vahidi/jdd/wiki/Home It includes two libraries for working with decision diagrams: - JBDD: a Java interface to two popular BDD libraries, CUDD and BuDDy - JDD: a native Java library supporting BDD, Z-BDD

Simulates a biologically diverse tropical island, and the ape inhabitants cognitive processes. For MacOS X, iPad, Windows and Linux. Features a non-polygonal graphics engine and a command-line version

Please click on "BROWSE ALL FILES" to open a README! What is this program? This program is meant to search the texts and suggest sentences that might follow any inputted sentence. It was meant to help composing the writings. How was it made? First, I made a chatterbot to understand the concept of "predicting" the next sentence (worked as good as the Cleverbot), then I made this program that is aided by an user to compose the new writings. SAMPLE: Input sentence was "Learning algorithm" The prefix was "transductive learning" Learning algorithm. Transduction, or transductive inference, tries to predict new outputs on specific and fixed (test) cases from observed, specific (training) cases. The simplest realization for transductive inference is the method of k-nearest neighbors. Learning to learn learns its own inductive bias based on previous experience. ...AND SO ON.... Enjoy the program !

Soar is a general cognitive architecture for developing systems that exhibit intelligent behavior. Researchers all over the world, both from the fields of artificial intelligence and cognitive science, are using Soar for a variety of tasks.

Rule-action based term rewriting framework, designed be embedded in Java applications.

Maximum entropy is a powerful method for constructing statistical models of classification tasks, such as part of speech tagging in Natural Language Processing. Several example applications using maxent can be found in the OpenNLP Tools Library.

Natural intelligence is the utilization of naturally occurring logic. This naturally occurring logic provides concrete clues for organizing natural objects, like: - Grouping objects that belong together, - Separating objects that don't belong together, - Archiving objects that have become less important. Natural language and spatial information are sources of natural intelligence: - Natural language is providing concrete logic for organizing knowledge objects, - Spatial information provides concrete logic for organizing spatial objects (utilized in, e.g., self-driving cars). In this way, our brains know how to organize their knowledge and spatial information. I focus on natural language because this source of natural intelligence is hardly understood by scientists. Hence, the inability of Large Language Models to organize changes in their knowledge independently.

TimeSleuth discovers temporal decision rules. It also judges the (a)causality of the rules. TimeSleuth can discover rules that involve time: {if (rainy_yesterday = true) then rainy_today = true}, or {if (rainy_tomorrow = true) then rainy_today = true}.

This program is made to address two most common issues with the known classifying algorithms. First, over-training and second, shortage of data for a training of categories. Instead, each TXT file is a category on its own, rather than an assigned category. In a way, this is similar to clustering but not really a clustering algorithm since there is some training involved. The summarizer from Classifier4J has been adjusted to accept two inputs (lets call them A and B). Then, the summarizer gets trained with A to summarize a document B, and vice versa. This extracts a relevant structure for both documents (and thus avoids the over-training) which are then compared using the Vector-Space analysis to give a range of belonging of one document to another (and thus avoids the shortage of information). This method can be used to create the user-defined classes by merging texts of certain categories and then to calculate the relevant distances between the documents, but this is not necessary.

A discretization algorithm based on the Minimum Description Length. Implemented as a filter according to the standards and interfaces of WEKA, the Java API for Machine Learning. More Info: http://bruno-wp.blogspot.com/search/label/Software

backprop1 provides a simple three layer backpropagation neural network implemented in java. There are three demo programs to perform point classification, the XOR problem and character recognition.