Epsilonn | a Tool for the Abstract Speciication and Parallel Simulation of Neural Networks

In this article the neural network speciication language EpsiloNN is presented. From an abstract speciication that is independent of the target computer architecture, a simulation source program for a workstation or a parallel computer can be generated. Neurocomputers requiring xed-point data types and arithmetic are supported too. The language design is based on an uniied neural network model and allows an object-oriented speciication of synapses, neurons and networks. The optimal mapping of a neural network onto a parallel computer can be determined automatically and an eecient parallel simulation source code can be obtained from an EpsiloNN speciication by program transformations. A complete speciication of a radial basis function network is given as an example and the methodology for generating simulation source code is explained in detail.