Title :
A VLSI implementation of a parallel, self-organizing learning model
Author :
Stout, Matthew G. ; Salmon, Linton G. ; Rudolph, George L. ; Martinez, Tony R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Brigham Young Univ., Provo, UT, USA
Abstract :
This paper presents a VLSI implementation of the priority adaptive self-organizing concurrent system (PASOCS) learning model that is built using a multichip module (MCM) substrate. Many current hardware implementations of neural network learning models are direct implementations of classical neural network structures-a large number of simple computing nodes connected by a dense number of weighted links. PASOCS is one of a class of ASOCS (adaptive self-organizing concurrent system) connectionist models whose overall goal is the same as classical neural networks models, but whose functional mechanisms differ significantly. This model has potential application in areas such as pattern recognition, robotics, logical inference, and dynamic control
Keywords :
multichip modules; VLSI implementation; adaptive self-organizing concurrent system; connectionist models; digital CMOS; multichip module substrate; neural network learning models; self-organizing learning model; Adaptive systems; Binary search trees; Circuit simulation; Computer networks; Discrete event simulation; Logic; Network topology; Neural networks; Pattern recognition; Very large scale integration;
Conference_Titel :
Pattern Recognition, 1994. Vol. 3 - Conference C: Signal Processing, Proceedings of the 12th IAPR International Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6275-1
DOI :
10.1109/ICPR.1994.577207
