Software for ANN training on a Ring Array Processor

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper


Phil Kohn, Jeff Bilmes, Nelson Morgan, James Beck


Experimental research on Artificial Neural Network (ANN) algorithms requires either writing variations on the same program or making one monolithic program with many parameters and options. By using an object-oriented library, the size of these experimental programs is reduced while making them easier to read, write and modify. An efficient and flexible realization of this idea is Connection(cid:173) ist Layered Object-oriented Network Simulator (CLONES). CLONES runs on UNIX1 workstations and on the 100-1000 MFLOP Ring Array Processor (RAP) that we built with ANN algorithms in mind. In this report we describe CLONES and show how it is implemented on the RAP.