Published 1998 | Version v1
Publication

Design of an Analog CMOS Self-Learning Multilayer Perceptron Chip

Description

In this paper we present the analog CMOS design of a multi-layer-perceptron network with on-chip by-pattern back-propagation learning. The learning algorithm is based on a local learning rate adaptation technique which makes the on-chip implementation more efficient in terms of convergence speed. Circuit simulation results validate the network behavior

Additional details

Identifiers

URL
http://hdl.handle.net/11567/201486
URN
urn:oai:iris.unige.it:11567/201486

Origin repository

Origin repository
UNIGE