Title :
A new VLSI architecture for large Hopfield´s neural networks
Author :
Verleysen, M. ; Sirletti, B. ; Jespers, P.
Author_Institution :
Laboratory of microelectronics, Université Catholique de Louvain, 3 pi. du Levant, 1348 Louvain-la-Neuve, Belgium; I.R.S.I.A. fellowship in the field of neural networks.
Abstract :
A new CMOS architecture for Hopfield´s neural networks is proposed. The use of differential amplifiers and active synapses allows the implementation of hundreds of neurons on a single chip. Since it is fully programmable, the circuit can be used as a content-addressable memory as well as in optimization problems.
Keywords :
Artificial neural networks; Biological neural networks; Biological system modeling; Hopfield neural networks; Microelectronics; Neural networks; Neurons; Pattern recognition; Very large scale integration; Voltage;
Conference_Titel :
Solid-State Circuits Conference, 1988. ESSCIRC '88. Fourteenth European
Conference_Location :
Manchester, UK
