Title :
A CMOS analog neuro-chip with stochastic learning and multilevel weight storage
Author :
Conti, Massimo ; Guaitini, Giovanni ; Turchetti, Claudio
Author_Institution :
Dept. of Electron., Ancona Univ., Italy
Abstract :
The chip, fabricated in a 1.0 μm CMOS technology, has a 2-dimension input vector, 16 neurons, 112 weights, each one with a multilevel storage circuit, 28 internal uncorrelated noise sources, a random weight change learning algorithm implemented on-chip and weight access capability
Keywords :
CMOS analogue integrated circuits; learning (artificial intelligence); neural chips; speech recognition; stochastic processes; 1.0 micron; CMOS analog neuro-chip; internal uncorrelated noise sources; multilevel weight storage; random weight change learning algorithm; stochastic learning; two-dimension input vector; weight access capability; CMOS technology; Circuit noise; Coupling circuits; Decoding; Differential equations; IEEE members; Neural networks; Neurons; Phased arrays; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1997. ISCAS '97., Proceedings of 1997 IEEE International Symposium on
Print_ISBN :
0-7803-3583-X
DOI :
10.1109/ISCAS.1997.621507
