Using a general-purpose neural network simulation tool—NEUCOMP—for character recognition problems

✍ Scribed by M.N. Sulaiman; D.J. Evans

• Publisher: Elsevier Science
• Year: 1995
• Weight: 994 KB
• Volume: 18
• Category: Article
• ISSN: 0745-7138
• DOI: 10.1016/s0745-7138(95)80023-9

✦ Synopsis

NEUCOMP is a neural network compiler that compiles a program written as a list of mathematical specifications of neural network (NN) models and then translates it into a chosen target program. A simulation program written in the NEUCOMP language based on selected NN models for solving character recognition problems is presented. The models are the Multilayer, Counterpropagation, Kohonen self-organizing networks, and Adaptive Resonance Theory (ART), which are chosen for their differences in architecture and learning algorithms. The program runs on the Sequent Balance machine at PARC.