The Sparse Blume\tire Emery\tire Griffiths Model of Associative Memories

J. Heusel, M. Lowe

2018, v.24, Issue 5, 779-810

ABSTRACT

We analyze the Blume\tire Emery\tire Griffiths (BEG) associative memory with sparse patterns and at zero temperature.
We give bounds on its storage capacity provided that we want the stored patterns to be
fixed points of the retrieval dynamics. We compare our results to that of other models of sparse neural networks and
show that the BEG model has a superior performance compared to them.

Keywords: Associative memory, storage capacity, sparse data, artificial intelligence, machine learning, exponential inequalities, negative association

COMMENTS

Please log in or register to leave a comment


There are no comments yet