SigmaPi is a simulator for recurrent neural networks of arbitrary topology. It uses the LSTM neuron model, and implements a training algorithm based on RTRL with some extensions taken from RProp.
Information regarding Project Releases and Project Resources. Note that the information here is a quote from Freecode.com page, and the downloads themselves may not be hosted on OSDN.
A more comfortable user interface, a new validation signal, new neuron icons, minor bugfixes, easier changing of training parameters, and use of the 'Gradient Squashing' technique.
