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.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2019.09.021 | DOI Listing |
Publication Analysis
Top Keywords
episodic memory
12
propose model
8
memory hierarchy
4
hierarchy spatiotemporal
4
spatiotemporal concepts
4
concepts propose
4
model
4
model episodic
4
memory consists
4
consists hierarchy
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!