Training a network with ternary weights using the CHIR algorithm

S Abramson; D Saad; E Marom

doi:10.1109/72.286901

Training a network with ternary weights using the CHIR algorithm

IEEE Trans Neural Netw. 1993;4(6):997-1000. doi: 10.1109/72.286901.

Authors

S Abramson¹, D Saad, E Marom

Affiliation

¹ Fac. of Eng., Tel Aviv Univ.

PMID: 18276532
DOI: 10.1109/72.286901

Abstract

A modification of the binary weight CHIR algorithm is presented, whereby a zero state is added to the possible binary weight states. This method allows solutions with reduced connectivity to be obtained, by offering disconnections in addition to the excitatory and inhibitory connections. The algorithm has been examined via extensive computer simulations for the restricted cases of parity, symmetry, and teacher problems, which show convergence rates similar to those presented for the binary CHIR2 algorithm, but with reduced connectivity. Moreover, this method expands the set of problems solvable via the binary weight network configuration with no additional parameter requirements.