Neurologic localization: Learning, knowledge representation, and generalization by a neural network model

Preston C. Calvert, Thomas R. Price

Research output: Contribution to journalConference articlepeer-review

Abstract

The cognitive process of neurologic localization was modeled with a neural network trained on real-world data error backpropagation learning. The task for the network involved learning an internal representation of the mapping from neurological examination findings to the computed tomography (CT) scan lesion distribution implied by those findings in acute stroke cases. The ability of the trained network to localize neurologic exam findings to CT lesion patterns in cases on which it had not been trained was tested. The network showed definite, but limited, ability to generalize from its training experience. There was a tendency for generalization to improve with increasing numbers of hidden units. The possible reason for the limitations of the performance of this model are discussed, and directions for further work are explored. A brief summary of some recent literature on the generalization problem in neural networks is presented.

Original languageEnglish (US)
Pages (from-to)283-287
Number of pages5
JournalProceedings - Annual Symposium on Computer Applications in Medical Care
StatePublished - Dec 1 1989
Externally publishedYes
EventProceedings: Thirteenth Annual Symposium on Computer Applications in Medical Care (SCAMC-13) - Washington, DC, USA
Duration: Nov 5 1989Nov 8 1989

ASJC Scopus subject areas

  • Engineering(all)
  • Medicine(all)

Fingerprint Dive into the research topics of 'Neurologic localization: Learning, knowledge representation, and generalization by a neural network model'. Together they form a unique fingerprint.

Cite this