Hebbian learning and temporary storage in the convergence-zone model of episodic memory

Citation
M. Howe et R. Miikkulainen, Hebbian learning and temporary storage in the convergence-zone model of episodic memory, NEUROCOMPUT, 32, 2000, pp. 817-821
Citations number
8
Language
INGLESE
art.tipo
Article
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
NEUROCOMPUTING
ISSN journal
0925-2312 → ACNP
Volume
32
Year of publication
2000
Pages
817 - 821
Database
ISI
SICI code
0925-2312(200006)32:<817:HLATSI>2.0.ZU;2-P
Abstract
The convergence-zone model shows how sparse, random memory patterns can lea d to one-shot storage and high capacity in the hippocampal component of the episodic memory system. This paper presents a biologically more realistic version of the model, with continuously weighted connections and storage th rough Hebbian learning and normalization. In contrast to the gradual weight adaptation in many neural network models, episodic memory turns out to req uire high learning rates. Normalization allows earlier patterns to be overw ritten, introducing time-dependent forgetting similar to the hippocampus. ( C) 2000 Published by Elsevier Science B.V. All rights reserved.