Title :
A 20 Tera-CPS analog neural network board
Author :
Murasaki, Mitsuhiro ; Arima, Yutaka ; Shinohara, Hirofumi
Author_Institution :
Semicond. Res. Lab., Mitsubishi Electr. Corp., Itami, Japan
Abstract :
Demonstrates an analog neural network board which integrates 18 interconnected neural network chips. The board realizes a fully feedback connection network consisting of 1,008 neurons and 1,016,064 synapses. The speed performance of the neural network is 20×1012 connections per second (CPS) and 500×109 connections update per second (CUPS).
Keywords :
feedback; neural chips; 20 Tera-CPS analog neural network board; fully feedback connection network; interconnected neural network chips; Capacitance; Capacitors; Character recognition; Digital signal processing chips; Image recognition; Image restoration; Laboratories; Neural networks; Neurofeedback; Neurons;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714358