Title :
An architecture for learning to behave
Author :
Aitken, Ashley M.
Author_Institution :
Sch. of Comput. Sci. & Eng., New South Wales Univ., Kensington, NSW, Australia
fDate :
27 Jun-2 Jul 1994
Abstract :
The SAM architecture is a novel neural network architecture, based on the cerebral neocortex, for combining unsupervised learning modules. When used as part of the control system for an agent, the architecture enables the agent to learn the functional semantics of its motor outputs and sensory inputs, and to acquire behavioral sequences by imitating other agents (learning by `watching´). This involves attempting to recreate the sensory sequences the agent has been exposed to. The architecture scales well to multiple motor and sensory modalities, and to more complex behavioral requirements. The SAM architecture may also hint at an explanation of several features of the operation of the cerebral neocortex
Keywords :
brain models; neural net architecture; neural nets; software agents; unsupervised learning; SAM architecture; agent; behavioral requirements; behavioral sequences; cerebral neocortex; control system; functional semantics; learning by watching; learning to behave; motor outputs; multiple motor; neural network architecture; sensory inputs; sensory modalities; sensory sequences; unsupervised learning; Animals; Artificial intelligence; Australia; Biological neural networks; Computer architecture; Computer science; Control systems; Laboratories; Supervised learning; Unsupervised learning;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374286
