Title: Bipolar pattern association using a 2-layer feedforward neural-network
Authors: Hao, Jb ×
Tan, Sh
Vandewalle, Joos #
Issue Date: Dec-1993
Publisher: Ieee-inst electrical electronics engineers inc
Series Title: IEEE Transactions on circuits and systems i-fundamental theory and applications vol:40 issue:12 pages:943-946
Abstract: The objective of this paper is to present a design technique that constructs a two-layer feedforward network for the realization of an arbitrary set of bipolar associations (p(i), q(i)), i = 1,...,k. The underlying idea is to use a layer of the hard-logic neurons to identify each p(i) in the winner-take-all fashion. Then the second layer of the so-called sign neurons picks up the corresponding pattern q(i). An important feature of the net is that it can be used as an error-correcting associative memory if the thresholds of the hard-logic neurons in the first layer are properly adjusted.
ISSN: 1057-7122
Publication status: published
KU Leuven publication type: IT
Appears in Collections:ESAT - STADIUS, Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics
× corresponding author
# (joint) last author

Files in This Item:

There are no files associated with this item.

Request a copy


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science