Search Results for "gnu science" - Page 7

Extensible framework that enables productive design, analysis, and execution of arbitrary-sized neural-networks or system on a distributed, scalable, high-throughput runtime platform. Enables synapse-oriented-programming.

The project goal is to develop several IP cores that would implement artificial neural networks using FPGA resources. These cores will be designed in such a way to allow easy integration in the Xilinx EDK framework.

Highly reusable and extensible Decision-Tree (Max-Gain) framework comprising of comprehensive input-processing and display functionality. Handles nominal, linear, continuous data. For preliminary description, refer - http://sushain.com/blog/archives/

A Java application that tries to learn the ontology of sport articles in German newspapers.

ANT is a lightweight implementation in C of a kind of artificial neural net called Multilayer Perceptron, which uses the backpropagation algorithm as learning method. The package includes an introductory example to start using artificial neural nets.

TrimGA is a lightweight genetic algorithm library written in pure Java 6.0 that can be quickly applied to most optimization problems.

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 project aimed at creating framework and binary data format for etymological Arabic system. and will not continue hosted at sourceforge because the term of use determine me as enemy, so I am prohibited from using sourceforge services.

Betelgeuse is a machine learning modeling package designed to meet the requirements of heavy-duty industry use. It was designed to be efficient, reliable, and highly modular; it is developed primarily in Python to promote maintainability and rapid development, but uses Cython and C in critical bottlenecks for efficiency. It focuses on high-quality implementations of a diverse set of the most widely used machine learning algorithms. An important goal of Betelgeuse is to have a clean,...

pySPACE is a modular software for processing of large data streams that has been specifically designed to enable distributed execution and empirical evaluation of signal processing chains. Various signal processing algorithms (so called nodes) are available within the software, from finite impulse response filters over data-dependent spatial filters (e.g. CSP, xDAWN) to established classifiers (e.g. SVM, LDA). pySPACE incorporates the concept of node and node chains of the MDP framework. Due...

lstm network library

UnBFuzzy is an API for fuzzy-logic and learning algorithms for fuzzy systems.

The open source project to port image analysis MaZda program to Linux and OS X platforms. See: http://www.eletel.p.lodz.pl/programy/mazda/

A fast kernel density estimation based classifier. Uses multi resolution KD trees to significantly reduce the number of calculations needed to perform density estimation.

A mobile application to identify plant images. A portable botanist at your fingertips.

Supertagging is a process of statistical lexical disambiguation, preprocessing step to parsing, which assigns LTAG tree categories to the lexical items present in the input sentence. Thus, if the input sentence is in the form of a dependency tree, the task of the supertagger is to assign the most probable TAG family to each node and edge in the dependency tree.

Data Mining Platform is a platform for data mining and analysis. It contains many of the new and sophisticated methods such as kernel-based classification, two-way clustering, bayesian networks, pattern recognition for time series analysis and many other

a distributed engine for abstract neural network development via natural-language programming

ExoPlanet provides a graphical interface for the construction, evaluation and application of a Machine Learning model in predictive analysis. With the back-end built using the numpy and scikit-learn libraries, as a toolkit, ExoPlanet couples fast and well tested algorithms, a UI designed over the Qt4 framework, and graphs rendered using Matplotlib to provide the user with a rich interface, rapid analytics and interactive visuals. ExoPlanet is designed to have a minimal learning curve,...