Object-Oriented Neural Simulation Tools For A Hypercube Parallel Machine

A substantial amount of work has recently been completed at the University of Central Florida in the development of an Artificial Neural Network (ANN) simulation environment that overcomes traditional implementation problems normally associated with these types of programs. Researchers addressing the development and application of ANN systems seek modifiability, expansibility and platform independence. Our system allows for these elements as well as parallel execution when a parallel hardware is available. This is accomplished by use of object-oriented programming and a Computer Aided Software Engineering (CASE) approach to the development environment that allows the user to modify the software describing the ANN model without understanding of the overall implementation details. A sophisticated Graphical User Interface (GUI) is provided to allow rapid construction and evaluation of complex large-scale neural models. © 1992