Magazine:
Storage capacity comparison of neural network models for memory recall
The physiology of how the human brain recalls memories is not well understood. Neural networks have been used in an attempt to model this process. Two types of networks have been used in several models of temporal sequence memory for simple sequences of randomly generated and also of structured patterns: auto- and hetero-associative networks. Previous work has shown that a model with coupled auto- and hetero-associative continuous attractor networks can robustly recall learned simple sequences. In this paper, we compare Hebbian learning and pseudo-inverse learning in a model for recalling temporal sequences in terms of their storage capacities.
Storage capacity comparison of neural network models for memory recall
Full text also available in the ACM Digital Library as PDF | HTML | Digital Edition
Thank you for your interest in this article. This content is protected. You may log in with your ACM account or subscribe to access the full text.