DEVS has been developed for over a year to serve as an experimental framework for natural systems modeling techniques. It enables discrete event, general purpose, object oriented, component based, GIS connected, and collaborative visual simulation model development and execution. The sample model implementation shows that this experimental environment can be used for solving any complex problems solvable by discrete-event simulation, but it is especially suited for natural system simulation. Currently only hierarchical block and cellular models are modeled and simulated, but a multi-layered modeling paradigm for spatially distributed systems (with vector and cellular models) will eventually be implemented in the environment.
WEBWEAVR-III is a research toolkit that supports the construction of Bayesian networks, inference in standard and dynamic Bayesian networks and decomposable Markov networks, the construction and verification of multiply sectioned Bayesian networks (MSBNs), inference in multi-agent MSBNs, and learning decomposable Markov networks.
Raiden is an extremely lightweight and fast block cipher, developed using genetic programming. Its aims are to be simple enough to be remembered by heart and to be compact, highly portable, and light enough to be implemented in resource constrained environments. It was developed with the intention of being an alternative to TEA, with the same speed and without any of its known weaknesses.
PED is a dialogue management system that uses a probabilistic nested belief model to choose dialogue strategies. The dialogue system designer need only supply a set of plan rules to PED as a dialogue grammar with preconditions. Using this grammar, PED constructs game trees (like the one below) to represent the outcomes of the dialogue, so that a dialogue strategy can be chosen for the current turn in the dialogue. PED automatically maintains a belief model by a belief revision process that uses the observed acts in the dialogue. The game tree is evaluated in the context of this belief model. PED is efficient because it uses probabilistic estimates of belief rather than a plain logical belief model.
SHOGUN is a machine learning toolbox whose focus is on large scale kernel methods and especially on Support Vector Machines (SVM). It provides a generic SVM object interfacing to several different SVM implementations, all making use of the same underlying, efficient kernel implementations. Apart from SVMs and regression, SHOGUN also features a number of linear methods like Linear Discriminant Analysis (LDA), Linear Programming Machine (LPM), (Kernel) Perceptrons, and algorithms to train hidden Markov models. SHOGUN can be used from within C++, Matlab, R, Octave, and Python.
Evolving Games for Unnatural Intelligence is a Java package for unsupervised machine learning based on Evolutionary Game Theory on directed graphs. It is able to segment data without any previuos information on the number of segments. It has no GUI, but implements generalizations of the original method proposed by Li, Chen, He and Jiang in the arxiv paper "A Novel Clustering Algorithm Based Upon Games on Evolving Network", published on 30 Dec 2008.
pyuds is a Python library for measuring uncertainty in the Dempster-Shafer theory of evidence. The functionals supported are the Generalized Hartley (GH) uncertainty functional, Generalized Shannon (GS) uncertainty functional, and Aggregate Uncertainty (AU) functional. The library can be utilized either through its API, or through a user-friendly Web interface.
Daikon is an implementation of dynamic detection of likely invariants. An invariant is a property (such as "x=2*y+5" or "this.next.prev = this" or "myarray is sorted by <") that holds at a certain point or points in a program. Invariants are often seen in assert statements, documentation, and formal specifications. Invariants can be useful in program understanding and a host of other applications. Daikon runs a program, observes the values that the program computes, and then reports properties that were true over the observed executions. It can detect properties in Java, C, C++, Perl, and IOA programs, in spreadsheet files, and in other data sources.
Fuzzy sets for Ada is a library providing implementations of confidence factors with the operations not, and, or, xor, +, and *, classical fuzzy sets with the set-theoretic operations and the operations of the possibility theory, intuitionistic fuzzy sets with the operations on them, fuzzy logic based on the intuitionistic fuzzy sets and the possibility theory; fuzzy numbers, both integer and floating-point with conventional arithmetical operations, and linguistic variables and sets of linguistic variables with operations on them. String-oriented I/O is supported. A rich set of GTK+ GUI widgets is provided.