DocumentCode
2973385
Title
A radial basis function neural network with on-chip learning
Author
Park, Chin ; Buckmann, Kenneth ; Diamond, Jay ; Santoni, Umberto ; The, Siang-Chun ; Holler, Mark ; Glier, Michael ; Scofield, Christopher L. ; Nunez, Linda
Author_Institution
Intel Corp., Santa Clara, CA, USA
Volume
3
fYear
1993
fDate
25-29 Oct. 1993
Firstpage
3035
Abstract
A radial basis function neural network is implemented in a 0.8 μm Flash EPROM CMOS technology. The RBF network is used to estimate probability density functions for the purpose of pattern recognition. At 40 MHz this 3.7 M transistor chip performs 20 billion 5 b integer subtract and accumulate operations/s and 160 MFLOPS.
Keywords
CMOS integrated circuits; EPROM; feedforward neural nets; learning (artificial intelligence); neural chips; pattern recognition; probability; 0.8 μm Flash EPROM CMOS technology; 3.7 M transistor chip; 40 MHz; on-chip learning; pattern recognition; probability density functions; radial basis function neural network; Circuits; EPROM; Educational institutions; Network-on-a-chip; Pattern recognition; Probability density function; Prototypes; Radial basis function networks; Speech; Very large scale integration;
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.1993.714360
Filename
714360
Link To Document