Show simple item record

dc.contributor.author Bieszczad, Kasia en
dc.contributor.author Bieszczad, Andrzej en
dc.date.accessioned 2007-09-06 en
dc.date.available 2007-09-06 en
dc.date.issued 2006 en
dc.identifier.citation Bieszczad, Andrzej and Bieszczad, Kasia. "Contextual learning in the Neurosolver." Lecture Notes in Computer Science. V. 4131 (2006): 474-484. en
dc.identifier.issn 0302-9743 en
dc.identifier.uri http://hdl.handle.net/10139/430 en
dc.description.abstract In this paper, we introduce an enhancement to the Neurosolver, a neuromorphic planner and a problem solving system. The enhanced architecture enables contextual learning. The Neurosolver was designed and tested on severalproblem solving and planning tasks such as re-arranging blocks and controlling a software-simulated artificial rat running in a maze. In these tasks, the Neurosolver learned temporal patterns independent of the context. However in the real world no skill is acquired in vacuum; Contextual cues are a part of every situation, and the brain can incorporate such stimuli as evidenced through experiments with live rats. Rats use cues from the environment to navigate inside mazes. The enhanced architecture of the Neurosolver accommodates similar learning. en
dc.language.iso en en
dc.publisher Springer en
dc.subject artificial neural networks en
dc.subject connectionist cognitive science en
dc.title Contextual learning in the Neurosolver en
dc.type Postprint en
dc.contributor.csuciauthor Bieszczad, Andrzej en

Files in this item


This item appears in the following Collection(s)

Show simple item record

Search DSpace

My Account

RSS Feeds