Spin-L: sequential pipelined neuroemulator with learning capabilities

Author

Barber, Steven M. ; Delgado-Frias, Jose G. ; Vassiliadis, Stamatis ; Pechanek, Gerald G.

Author_Institution

Dept. of Electr. Eng., State Univ. of New York, Binghamton, NY, USA

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1927

Abstract

In this paper, an extensive study of learning and retrieval algorithms for Hopfield´s pattern classifier network, multilayer backpropagation, Kohonen´s self-organized feature mapping network, and the binary adaptive resonance theory (ART-1) models is reported. Parallelism as well as computational requirements are identified for all algorithms. The algorithms are then mapped onto the sequential pipelined neuroemulator (SPIN) architecture. As a result, the SPIN with learning (SPIN-L) machine is developed as an enhanced architecture to accommodate the new requirements.

Keywords

ART neural nets; Hopfield neural nets; backpropagation; pattern classification; pipeline processing; self-organising feature maps; virtual machines; ART-1 models; Hopfield pattern classifier network; Kohonen self-organized feature mapping network; Spin-L; binary adaptive resonance theory; learning; learning algorithms; learning capabilities; multilayer backpropagation; retrieval algorithms; sequential pipelined neuroemulator; Artificial neural networks; Binary trees; Computer architecture; Computer networks; Costs; Hardware; Machine learning; Neural networks; Neurons; Resonance;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.717032

Filename

717032