Associative Learning via Inhibitory Search

Abstract

ALVIS is a reinforcement-based connectionist architecture that learns associative maps in continuous multidimensional environ(cid:173) ments. The discovered locations of positive and negative rein(cid:173) forcements are recorded in "do be" and "don't be" subnetworks, respectively. The outputs of the subnetworks relevant to the cur(cid:173) rent goal are combined and compared with the current location to produce an error vector. This vector is backpropagated through a motor-perceptual mapping network. to produce an action vec(cid:173) tor that leads the system towards do-be locations and away from don 't-be locations. AL VIS is demonstrated with a simulated robot posed a target-seeking task.

Cite

Text

Ackley. "Associative Learning via Inhibitory Search." Neural Information Processing Systems, 1988.

Markdown

[Ackley. "Associative Learning via Inhibitory Search." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/ackley1988neurips-associative/)

BibTeX

@inproceedings{ackley1988neurips-associative,
  title     = {{Associative Learning via Inhibitory Search}},
  author    = {Ackley, David H.},
  booktitle = {Neural Information Processing Systems},
  year      = {1988},
  pages     = {20-28},
  url       = {https://mlanthology.org/neurips/1988/ackley1988neurips-associative/}
}