Episodic memory: A hierarchy of spatiotemporal concepts.

Journal: Neural networks : the official journal of the International Neural Network Society
PMID:

Abstract

We propose a new model of episodic memory. It consists of a hierarchy of partial sequences of events, blended for consistency across space and time by feedforward/feedback links to concepts expressing their shared information. This blended concept hierarchy is acquired and represented incrementally through synaptic or connection-weighted adaptation in a neural network with episodic memory capability. We derive this model through argumentation, explain its derivation within a category-theoretic model of representation, and discuss the capabilities we propose for this model.

Authors

  • Michael J Healy
    Department of Electrical and Computer Engineering, MSC01 1100, University of New Mexico, ECE Bldg., Room 125, Albuquerque, NM 87131-0001, United States of America. Electronic address: mjhealy@unm.edu.
  • Thomas P Caudell
    Department of Electrical and Computer Engineering, MSC01 1100, University of New Mexico, ECE Bldg., Room 125, Albuquerque, NM 87131-0001, United States of America. Electronic address: tcaudell@unm.edu.