Encog is an advanced neural network and bot programming library. It can be used independently either to create neural networks or HTTP bot programs. It also includes classes that combine these two advanced features. It contains classes for Feedforward Neural Networks, Hopfield Neural Networks, and self organizing maps. Training can be accomplished using back-propagation, simulated annealing, and genetic optimization. Additional classes are provided for pruning neural networks. Encog also includes advanced HTTP bot programming features. A multi-threaded spider that can store its workload either in memory on a database is provided. HTML parsing is provided, as well as advanced form and cookie handling.
|Tags||Scientific/Engineering Artificial Intelligence|
Release Notes: This is a very major upgrade. Using OpenCL, you can now use your GPU(s) to help accelerate neural network training. Other additions include Neuroevolution of Augmenting Topologies (NEAT), Levenberg Marquadt, and ENcog Cloud.
Release Notes: This update is much faster and includes extensive multicore support. This is an important update for Encog. It includes many bugfixes from 2.1.0, as well as some important new features, such as considerable performance improvements, MPROP training (similar to RPROP, but tuned for MultiCore), a built-in normalization class.
Release Notes: This version adds many new network types and training methods for neural networks. Encog allows you to construct neural network applications in Java or C#. The neural network architectures it supports are feedforward neural network (Perceptron), Hopfield neural network, self organizing map (Kohonen), radial basis function network, Elman recurrent neural network, and Jordan recurrent neural network.
Release Notes: This is a major update to the Encog Neural Network and Bot framework. It adds the Encog workbench, which is a GUI tool that can be used to edit the .EG files that Encog uses to save neural networks and training data. The workbench can be used to construct all neural network types that Encog supports, such as Hopfield, Feedforward, and Self Organizing Maps. Training can also be performed using the workbench. The workbench can generate Java, C# and Visual Basic code for the neural networks that you create. Additionally, there have been several bugfixes and enhancements to the core JAR.
No changes have been submitted for this release.