Search Results for "engineering"

Kohonen neural network library is a set of classes and functions for design, train and use Kohonen network (self organizing map) which is one of AI algorithms and useful tool for data mining and discovery knowledge in data (http://knnl.sf.net).

This Ruby program takes in a topology specification for an artificial neural network and emits optimized C code (using SSE intrinsics) that implements fast forward and backward propagation for that specific topology.

A parallel-programming framework for concurrently running large numbers of small autonomous jobs, or microthreads, across multiple cores in a CPU or CPUs in a cluster. NeuraNEP emulates a distributed processing environment capable of handling millions of microthreads in parallel, for example running neural networks with millions of spiking cells. Microthreads are general processing elements that can also represent non-neural elements, such as cell populations, extracellular space, emulating...

Code of this library is partialy based on myCNN MATLAB class written by Nikolay Chemurin.

[Open Artificial Intelligence Library]. This library main goal is to provide a tool box to those who want to use algorithm such as neural network or genetics Algorithm and all algorithms that are commonly within the Artificial Intelligence field.

...NeuraNEP (sourceforge.net/projects/neuranep) represents a major update to SpikeOS. It has the same core functionality plus several enhancements, including a scripting interface. NeuraNEP is engineering-oriented, as opposed to simulation-oriented, and some features/capabilities have changed.

It's an object-oriented library written in C++ for creating arbitrary kind of neural networks. The user can use the classes provided to create neural network with arbitrary topology and mixed type of neurons. It's very easy add custom neurons.

Syntactic is a simple C++ library for constructing general Neural networks. For now the library supports creation of multi layered networks for the Feedforward Backpropagation algorithm as well as Time Series Networks. More will be implemented soon.

Foad is an open source software which receive an EKG Signal from scanner, WFDB database or heart sensors. Finding patient disease started by taking Fourier transform (FFT) from input signal and extract a single cycle. Based on some heuristic algorithm the most important feature like P , Q , R , S , T captured and feed to trained neural network. and so the final decision made by CNN library. As mentioned before this software also capable do some image processing on scanned paper to lower...

Yann is Yet Another Neural Network. Yann is a library to create fast neural networks. It is also a GUI to easily create, edit, train, execute and investigate networks. Multiple topologies, runtime properties and ensemble learning are supported.

The DAMNED simulator is a Distributed And Multithreaded Neural Event-Driven simulation framework designed for Distributed Discrete Event Simulations, actually well suited for Large Scale Spiking Neural Network simulations.

Neural Network class library: Its a C/C++ implementation that provides following three neural architecture - Feed-forward network, Radial Basis function network, multi-layer perceptron and Self-Organizing Maps.

Neural - is neural network engine with object-oriented design. Features: - Supports: backpropogation, RPROP algorithms. - Flexible input/outputs framework. - Distributed calculations.

This tool allows to compute LOLIMOT models. LOLIMOT models are also called neuro-fuzzy models or fast neural network models. This tool can export the model into C, C++, Matlab.

Lightweight backpropagation neural network in C++. The project provides a class implementing a feedforward neural network, and a class for easily train it. It is highly customizable to manage your problem and comes with a simple graphical interface.

TIKAPP is becoming a collection of tools for simulation of neural networks. The first available part is an ANSI-C++ library with support for backpropation networks.

Cluster Networks are a new style of neural simulation / neural network modeling, that models networks of neural populations ("clusters") that transform and transmit information using precisely-timed, graded bursts ("pulses" or "volleys") of firing.

Zeus is a small, lightweight, very fast object oriented framework for developing neural networks with an integrated shell interface.

RooCARDS is a set of C++ classes written for the ROOT analysis framework which interface ROOT to the Stuttgart Neural Network Simulator (SNNS). This interface is based on a concept originally developed by Professor Yibin Pan at the UW-Madison.