Scalable completely connected digital neural networks

Author

Pechanek, Gerald G. ; Vassiliadis, Stamatis ; Delgado-Frias, Jose G. ; Triantafyllos, George

Author_Institution

IBM Microelectron., Research Triangle Park, NC, USA

Volume

4

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

2078

Abstract

A machine organization is presented for the digital emulation of completely connected and multi-layer neural networks including back-propagation learning. The system architecture lends itself to a hierarchical machine organization of six levels and supports the direct emulation of network models for up to N neurons and the virtual emulation of an arbitrary number of V neurons for V>N. The system is scalable for both direct and virtual processing. Based on performance estimations, the proposed structure is shown to provide a 3X to 133X speed-up for NETtalk emulation when compared to other neuroemulators

Keywords

backpropagation; multilayer perceptrons; neural net architecture; parallel architectures; virtual machines; NETtalk emulation; backpropagation learning; digital emulation; hierarchical machine organization; multi-layer neural networks; neuroemulators; performance estimations; scalable completely connected digital neural networks; virtual emulation; virtual processing; Computer architecture; Emulation; Equations; Hopfield neural networks; Machine learning; Multi-layer neural network; Neural networks; Neurons; Silicon; Software performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374534

Filename

374534