Neural Net Algorithms

TDL - Win Neural Net Pattern Recog. Tool Quick, hassle-free automatic construction of NN by use of evolutionary processes. Trans-Dimensional Learning allows multiple data sets to be learned incrementally, regardless of differences in number of inputs and outputs. Complete graphical support of...

AI::NNFlex::Backprop project is a fast, pure perl backprop Neural Net simulator. SYNOPSIS use AI::NNFlex::Backprop; my $network = AI::NNFlex::Backprop->new(config parameter=>value); $network->add_layer(nodes=>x,activationfunction=>function); $network->init(); use...

AI::NeuralNet::BackProp is a simple back-prop neural net that uses Deltas and Hebbs rule. SYNOPSIS use AI::NeuralNet::BackProp; # Create a new network with 1 layer, 5 inputs, and 5 outputs. my $net = new AI::NeuralNet::BackProp(1,5,5); # Add a small amount of randomness to the network...


Platforms: *nix

Joone is a neural net framework written in Java(tm). It's composed by a core engine, a GUI editor and a distributed training environment and can be extended by writing new modules to implement new algorithms or architectures starting from base component


Platforms: Windows, Mac, Linux

v(1.0) fSC-Net - Win Neural Net Fuzzy Pattern Recognition. Quick, hassle-free automatic construction of Neural Networks. Incremental learning. Support of fuzzy logic. Hybrid symbolicconnectionist representation. Complete graphical support of training and testing. Point and click recall of network...


Platforms: Windows

Jannis stands for 'J Artificial Neural Net Interactive Simulator'.Jannis' primary purpose is simulation of neural net models for scientific experiments in special-needs-education and neuropsychology.


Platforms: Windows, Mac, Linux

This is a small framework for Q(0) with a feedforward-neural net. The example application is a agent in 2D, which learns to balance a pole.


Platforms: Windows, Mac, Linux

Java class libraries for structural biology development: includes protein format conversion tool, printf-based text formatting, Pred2ary secondary structure prediction, neural net library, Hooke-Jeeves global optimizer, and misc. math & statistics.


Platforms: Windows, Mac, Linux

AI::NeuralNet::Simple is a simple learning module for building neural nets. SYNOPSIS use AI::NeuralNet::Simple; my $net = AI::NeuralNet::Simple->new(2,1,2); # teach it logical or for (1 .. 10000) { $net->train([1,1],[0,1]); $net->train([1,0],[0,1]); $net->train([0,1],[0,1]);...


Platforms: *nix

This project provides matlab class for implementation of convolutional neural networks. This networks was developed by Yann LeCun and have sucessfully used in many practical applications, such as handwritten digits recognition, face detection, robot navigation and others (see references for more...


Platforms: Matlab

SHARK provides libraries for the design of adaptive systems, including methods for linear and nonlinear optimization (e.g., evolutionary and gradient-based algorithms), kernel-based algorithms and neural networks, and other machine learning techniques.


Platforms: *nix

FreeADSP stands for Free Audio Digital Signals Processor and is a free audio-oriented real-time DSP software. What it does is taking a signal as input, transform it through arbitrary-disposed modules, and then putting the result back to some output (that is, for example, the same thing that...


Platforms: *nix

Robust Particle Swarm toolbox implementing Trelea, Common, and Clerc types along with an alpha version of change detection.This toolbox is designed for researchers in Computational Intelligence as well as application developers, students, and classroom labs. It is robust enough that several...


Platforms: Matlab

Blue Moon AI is an artificial intelligence opponent for the card game Blue Moon All eight of the original Blue Moon people decks are supported, as well as the more recent Buka Invasion deck. About Blue Moon Blue Moon is a 2-player card game published in 2004, inspired by collectible card games...


Platforms: *nix

AKIRA aims to create a C++ development framework to build cognitive architectures and complex artificial intelligent agents.Features:KQML,Fuzzy Logic,Neural Net,Fuzzy Cognitive Maps and DIPRA (a distributed BDI - Belief Desire Intention goals model)


Platforms: *nix

The NSketch library provides implementations of most common sketch-based algorithms (histograms, quantile, frequent items, bloom filter ...). The library is written in C# for .Net.


Platforms: Windows, Mac, Linux

The form of a single layer feed forward neural network lends itself to finding the gradient. This is useful when the network is used for surrogate optimization or other algorithms that use gradients. Requires creating a file by modifying a NN toolbox file.


Platforms: Matlab

Implements symmetric encryption algorithms: Rijndael, Blowfish, Twofish. Also provides public-key encryption and decryption using digital certificates. Provides hashing functionality for both strings and binary data using SHA1, SHA384, SHA512, MD2, MD5, and HAVAL. Provides BZIP2 compression for...


Platforms: Windows

Open source, fast and simple neural processing MATLAB scripts, functions and algorithms. File IO, spike detection, signal processing, seizure detection, closed loop. Functions are compatible with Blackrock Microsystems NEV and NSx files.


Platforms: Windows, Mac, Linux

This project provides a set of Python tools for creating various kinds of neural networks, which can also be powered by genetic algorithms using grammatical evolution. MLP, backpropagation, recurrent, sparse, and skip-layer networks are supported.


Platforms: Windows, Mac, Linux