Encog Java and DotNet Neural Network Framework

About the Encog Project

Encog is an advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trains using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks. Encog has been in active development since 2008.

Encog is available for Java, .Net and Silverlight.

[Online Silverlight Demo]

[Report a Bug/Issue]

Encog's Supported Platforms

Java

Microsoft .Net & Silverlight

[Hudson - Development Alpha/Perhaps Unstable Release]

Training Techniques

Backpropagation
Resilient Propagation (RPROP)
Scaled Conjugate Gradient (SCG)
Manhattan Update Rule Propagation
Competitive Learning
Hopfield Learning
Levenberg Marquardt (LMA)
Genetic Algorithm Training
Instar Training
Outstar Training
ADALINE Training

Training Data Models

Supervised
Unsupervised
Temporal (Prediction)
Financial (downloads from Yahoo Finance)
SQL
XML
CSV
Image Downsampling

Activation Functions

Competitive
Sigmoid
Hyperbolic Tangent
Linear
SoftMax
Tangential
Sin Wave
Step
Bipolar
Gaussian

Randomization Techniques

Range Randomization
Gaussian Random Numbers
Fan-In
Nguyen-Widrow

Encog Links

[Encogware Store] - Mouse mats, t-shirts, etc. I use these for conferences, but if you want something with the Encog Neuron on it, here you go!
Version History - Encog version history.
Wiki - Encog Wiki.
Hudson Build Server - Our build server, you can get the very latest beta versions of Encog here. They are usually NOT as stable as our regular releases though. You can also see what the developers are working on here.
Using Encog with NinjaTrader.