New gradient learning rules for artificial neural nets based on moderatism and feedback model

Moderatism (Y. Okabe, 1998), which is a learning model for ANNs, is based on the principle that individual neurons and neural nets as a whole try to sustain a "moderate" level in their input and output signals. In this way, a close mutual relationship with the outside environment is maintained. In this paper, two potential moderatism-based local, gradient learning rules are proposed. Then, a pattern learning experiment is performed to compare the learning performances of these two learning rules, the error based weight update (EBWU) rule (M. Tanvir Islam et al., 2001), and error backpropagation (Christopher M. Bishop, 1995).