BioJava aims to provide a comprehensive set of Java components for the rapid development of applications in Bioinformatics. It contains interfaces for representing Sequences, Features, and other important bioinformatics concepts. It can also read and write sequence data in a variety of common formats and communicate with Ensembl databases and with DAS and BioCorba servers.
Maximum entropy is a powerful method for constructing statistical models of classification tasks, such as part-of-speech tagging in Natural Language Processing. The Quipu Maximum Entropy Package is a Java implementation of the maximum entropy framework. It allows you to train, evaluate, and use maxent models.
Torch is a machine learning library written in C++ that works on most Unix/Linux platforms. It can be used to train MLPs, RBFs, HMMs, Gaussian Mixtures, Kmeans, Mixtures of experts, Parzen Windows, KNN, and can be easily extended so that you can add your own machine learning algorithms.
The Freehand Formula Entry System is a research prototype for recognizing online handwritten mathematical notation, developed jointly by researchers in New Zealand, the United States and Canada. A user draws expressions with a mouse or data tablet, and LaTeX, a bitmap, and an operator tree are produced as output. Symbol recognition and expression interpretation are performed as the user draws.
Koalog Constraint Solver is a powerful constraint solver written in Java. It provides cutting-edge technology for solving satisfaction and optimization problems, including scheduling, time-tabling, resource-allocation, puzzles (sudoku.koalog.com is powered by Koalog Constraint Solver), and configuration (Koalog Configurator is powered by Koalog Constraint Solver).
Lindenmayer Systems in Python provides a simple implementation of Lindenmayer systems (also called "L-systems" or "substitution systems"). In basic form, a Lindenmayer system consists of a starting string of symbols from an alphabet which has repeated transitions applied to it, specified by a list of transition search-and-replace rules. In addition to the standard formulation, two alternative implementations are included: sequential systems (in which at most one rule is applied) and tag systems (in which the transition only takes place at the beginning and end of the string). Despite being implemented entirely in Python, for reasonable rules on a modern machine, the system is capable of running thousands of generations per second. Lindenmayer systems are found in artificial intelligence and artificial life and can be used to generate fractal patterns (usually via mapping symbols from the alphabet to turtle commands), organic-looking patterns that can simulate plants or other living things, or even music.