Influence of Refractory Periods in the Hopfield model
C. R. da Silva (CBPF, Universidade Federal de Alagoas, Brazil), F., A. Tamarit (FaMAF, Universidad Nacional de Cordoba, Argentina), E. M. F., Curado (CBPF, ICCMP, Brazil)
TL;DR
This paper investigates how incorporating refractory periods into the Hopfield model affects its associative memory retrieval and dynamic behavior through analytical and numerical methods.
Contribution
It introduces refractory periods as state-dependent thresholds in the Hopfield model and analyzes their impact on network performance and dynamics.
Findings
Refractory periods influence the stability of memory retrieval.
The dynamics of the network are altered by refractory periods.
Analytical and numerical results show changes in convergence behavior.
Abstract
We study both analytically and numerically the effects of including refractory periods in the Hopfield model for associative memory. These periods are introduced in the dynamics of the network as thresholds that depend on the state of the neuron at the previous time. Both the retrieval properties and the dynamical behaviour are analyzed.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.