Displaying 1 to 10 from 14 results

OpenCog - Framework to build Artificial Intelligence Programs

The OpenCog Framework is a platform to build and share artificial intelligence programs. It includes components for procedural and declarative knowledge representation (AtomSpace), task scheduling (CogServer), AI algorithm containers (MindAgents), connectors to instant messaging and virtual world systems, and other components. MindAgents and other add-ons explore a wide variety of AI techniques including evolutionary program learning (MOSES), natural language processing, and others.

Theano - Optimizing compiler for evaluating mathematical expressions on CPUs and GPUs.

Theano is a Python library that allows you to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays. It is built on top of NumPy. Its features include tight integration with NumPy, transparent use of a GPU, dynamic C code generation and lot more.

Deeplearning4J - Neural Net Platform in Java and Scala

Deeplearning4J is an open source, distributed neural net library written in Java and Scala. It integrates with Hadoop and Spark and runs on several backends that enable use of CPUs and GPUs. It provides versatile n-dimensional array class for Java and Scala.

Ksom - Kohonen Self-Organizing Map Library

KSOM is a portable implementation of the Kohonen Self-Organizing Map model written in C using the NetBeans 2.6.1 IDE. Also included is a Python module prototype of the library. The library itself compiles on both 64 bit Windows 7 and Ubuntu Linux without an issue. The example program "ksom_example" is not intended to be cross platform, though should compile on Linux with a few minor changes to the NetBeans project settings. The source code should not need modified. Linux and Windows binaries may

Neurolab - Simple and powerfull neural network library for python

NeuroLabNeurolab is a simple and powerful Neural Network Library for Python. Contains based neural networks, train algorithms and flexible framework to create and explore other networks. FeaturesPure python + numpy API like Neural Network Toolbox (NNT) from MATLAB Interface to use train algorithms form scipy.optimize Flexible network configurations and learning algorithms. You may change: train, error, initializetion and activation functions Variety of supported types of Artificial Neural Networ

Simbrain - A visually oriented, java-based neural network.

Welcome!This is the start page for information about Simbrain development. Simbrain is an open source project, and it goes without saying that we could use your help. If you've found a bug, can suggest an improvement to the interface, would like to add features, etc., join us, or feel free to post a message to our forum. BackgroundSimbrain is a java based neural network simulator which aims at providing a simple user interface and API. To get a sense of the design philosophy behind Simbrain, che

Back-Propagation Neural Networks Simulation

This is simple Back-Propagation Neural Network simulation using C#. This code is a part of my "Supervised Neural Network" book written in 2006.

Neural Cryptography in F#

This project is my magistracy resulting work. It is intended to be an example of using neural networks in cryptography. Hashing functions are chosen as the first step in this broad topic. Implementation language is F# running under .NET 4.0 with VS 2010 RC

Neural Network Basic

Neural Network Basic contain implementation of simple and effective implementation of neural network. Functionality it is developed in C++ native programming language, with use STL and Visual Studio C++ Express 2010.