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.
ASJC Scopus subject areas
- Statistical and Nonlinear Physics
- Mathematical Physics
- Physics and Astronomy(all)