Abstract
The storage capacity of a Q-state Hopfield network is determined via finite-size scaling for parallel dynamics and Q<or=8. The results are in good agreement with theoretical predictions by Rieger. The basins of attraction and other associative memory properties are discussed for Q=4, 6. A self-controlling Q-state model with improved basins of attraction is proposed.
Original language | English |
---|---|
Article number | 019 |
Pages (from-to) | 5919-5929 |
Number of pages | 11 |
Journal | Journal of Physics A: Mathematical and General |
Volume | 25 |
Issue number | 22 |
DOIs | |
Publication status | Published - 1992 |
ASJC Scopus subject areas
- Statistical and Nonlinear Physics
- Mathematical Physics
- General Physics and Astronomy