TRAINING A NETWORK WITH TERNARY WEIGHTS USING THE CHIR ALGORITHM

Authors
ABRAMSON S SAAD D MAROM E
Citation
S. Abramson et al., TRAINING A NETWORK WITH TERNARY WEIGHTS USING THE CHIR ALGORITHM, IEEE transactions on neural networks, 4(6), 1993, pp. 997-1000
Citations number
8
Categorie Soggetti
Computer Application, Chemistry & Engineering","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Hardware & Architecture","Computer Science Theory & Methods
Journal title
IEEE transactions on neural networks → ACNP
ISSN journal
10459227
Volume
4
Issue
6
Year of publication
1993
Pages
997 - 1000
Database
ISI
SICI code
1045-9227(1993)4:6<997:TANWTW>2.0.ZU;2-I
Abstract
A modification of the binary weight CHIR algorithm is presented, where by a zero state is added to the possible binary weight states. This me thod allows obtaining solutions with reduced connectivity, by offering disconnections in addition to the excitatory and inhibitory connectio ns. The algorithm was examined via extensive computer simulations for the restricted cases of parity, symmetry, and teacher problems, which show similar convergence rates to those presented for the binary CHIR2 algorithm, however, with reduced connectivity. Moreover, this method expands the set of problems solvable via the binary weight network con figuration with no additional parameter requirements.