Encog is an advanced neural network and bot programming library. Encog can be used independently either to create neural networks or HTTP bot programs. Encog also includes classes that combine these two advanced features. Encog contains classes for Feedforward Neural Networks, Hopfield Neural Networks, and self organizing maps. Training can be accomplished using backpropagation, simulated annealing, and genetic optimization. Additional classes are provided for pruning neural networks.

Encog also includes advanced HTTP bot programming features. A multithreaded 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.

Neural Network Architectures

• Feedforward Neural Network (Perceptron)
• Hopfield Neural Network
• Self Organizing Map (Kohonen)
• Radial Basis Function Network
• Elman Recurrent Neural Network
• Jordan Recurrent Neural Network

Training Techniques

• Backpropagation
• Resilient Propagation
• Manhattan Update Rule Propagation
• Competitive Learning
• Hopfield Learning
• Genetic Algorithm Training

Training Data Models

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

Activation Functions

• Sigmoid
• Hyperbolic Tangent
• Linear
• SoftMax
• Tangential
• Sin Wave
• Bipolar
• Gaussian