A habituation, rehabituation, and recovery chip
V.K. Goru, Lex A. Akers · 2002
In this paper, we present neural network modeling and chip design of a feature of habituation called "rehabituation". Habituation is a biological behavior allowing non-critical information to be disregarded enabling more processing resources for critical tasks. Rehabituation is an additional characteristic which allows a system to more rapidly disregard inputs when it has seen similar signals before. Recovery is the ability of a system to restore its ability to respond to a signal that has not occurred in some specified time period. An unsupervised learning rule is used to classify the input. Weight modification and frequency modulated output signal modules are implemented using mixed analog-digital CMOS circuits. We also propose an intelligent automatic door opening system based on these features.