𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Pattern recognition in the neocognitron is improved by neuronal adaptation

✍ Scribed by A. van Ooyen; B. Nienhuis


Publisher
Springer-Verlag
Year
1993
Tongue
English
Weight
686 KB
Volume
70
Category
Article
ISSN
0340-1200

No coin nor oath required. For personal study only.

✦ Synopsis


We demonstrate that equipping the neurons of Fukushima's neocognitron with the phenomenon that a neuron decreases its activity when repeatedly stimulated (adaptation) markedly improves the pattern discriminatory power of the network. By means of adaptation, circuits for extracting discriminating features develop preferentially. In the original neocognitron, in contrast, features shared by different patterns are preferentially learned, as connections required for extracting them are more frequently reinforced.