A novel large-memory neural network as an aid in medical diagnosis applications.

A novel large-memory neural network as an aid in medical diagnosis applications.

Describes the application of a LAMSTAR (LArge Memory STorage And Retrieval) neural network to medical diagnosis and medical information retrieval problems. The network is based on M.L. Minsky's (1980) knowledge lines (k-lines) theory of memory storage and retrieval in the central nervous system...

Description complète

Détails bibliographiques
Publié dans:IEEE Transactions on information technology in biomedicine 5, 3 (2001).
Auteur principal: Kordylewski, H.
Format: Article
Langue:English
Sujets:
Internet.
LAMSTAR neural net.
Adaptive system.
Address correlation.
Central nervous system.
Closed-loop operation.
Emergency-room drug identification.
Exact information.
Extrapolation.
Forgetting.
Fuzzy information.
Incomplete data sets.
Intelligent data use.
Interpolation.
K-lines.
Knowledge lines.
Large data sets.
Large memory storage and retrieval.
Large-memory neural network.
Learning hierarchy.
Link weight updating.
Medical diagnosis applications.
Medical information retrieval.
Nephrology.
Observed images.
Patient histories.
Patient interview information.
Pattern recognition.
Search engines.
Self-organized map module arrays.
Self-organizing feature map.
Test records.
Training speed.