

Preprint 55/2004
Adaptive Behaviour Control by Self-regulating Neurons
Frank Pasemann, Keyan Zahedi, and Marieke Rohde
Contact the author: Please use for correspondence this email.
Submission date: 25. Aug. 2004
Bibtex
Abstract:
A local learning rule for recurrent neural networks is derived
by introducing
neurons as self-regulating units. Acting as controllers for the behaviour
of autonomous mobile agents, neural systems endowed with this learning
rule generate interesting agent-environment interactions, which depend on the
underlying connectivity of the network. The dynamical phenomenology of a single
neuron and a two neuron network is analysed, and, as an example, the generation
of obstacle avoidance behaviour of a miniature Khepera robot is presented.