Computers

A standard environment for evaluating the performance of learning methods. Includes a number of datasets and an archive of learning methods.

Neural network for classification and regression problems. Supports ODBC and Excel.

A library of state-of-the-art machine learning algorithms. Licensed under the GPL, and designed for Unix and Linux environments.

A neural network based system to recognize leaves written in Java. A Java-Applet is also available.

Open-source software for simulating spiking neural networks, written in C++.

A platform for simulating complex neural systems.

Neural network software and Excel add-ins for forecasting and data analysis. Supports several algorithms. Trial versions are available.

Open-source neural network library for C++ (Windows and Linux). Support for MLP, RBF and Hopfield networks. Interfaces with Matlab's Neural Network Toolbox.

MS Excel add-ins based on neural networks. Designed for predicting, classification and financial forecasting.

A free java-based neural network simulation kit.

Icon-based neural network development software. Supports several types of networks and training algorithms. Trial version is available.

Free software project. Implements a general feed forward neural network and some training techniques.

An open source neural network library. Implements feedforward neural network classes in multiple languages including C++ and PHP.

Simulates MLP, RMLP and Cascade-Correlation models with dynamic size adjustment algorithms. Includes various training patterns, error and activation functions.

Tutorial that includes Java applet for online experiments with prediction of a function, including training set generation and error observation.

Suite of unsupervised competitive learning software written in Java, with full source code.

Java open source neural network framework which can be used to create and train common types of neural networks. Site contains full source code, documentation and project info.

An environment for neural network research, design, and simulation within MATLAB.

An open source library for numeric computation using data flow graphs, optimized for parallel processing using GPUs to handle massive scale deep neural network training. Offers documentation, tutorials and source code.

A Python neural network system built on top of Theano which provides transparent multi-core and GPU optimization for efficiently training multilayer convolutional neural networks.