Dynamical mean field approach to associative memory model with non-monotonic transfer functions
arXiv:2510.19146 · doi:10.1088/1742-5468/ae337e
Abstract
The Hopfield associative memory model stores random patterns in synaptic couplings according to Hebb's rule and retrieves them through gradient descent on an energy function. This conventional setting, where neurons are assumed to have monotonic transfer functions, has been central to understanding associative memory. Morita (1993, Neural Netw. 6 115), however, showed that introducing non-monotonic transfer functions can dramatically enhance retrieval performance. While this phenomenon has been qualitatively examined, a full quantitative theory remains elusive due to the difficulty of analysis in the absence of an underlying energy function. In this work, we apply dynamical mean-field theory to the discrete-time synchronous retrieval dynamics of the non-monotonic model, which succeeds in accurately characterizing its macroscopic dynamical properties. We also derive conditions for retrieval states, and clarify their relation to previous studies. Our results provide new insights into the non-equilibrium retrieval dynamics of associative memory models.
28 pages, 10 figures
References in corpus (7)
- A constructive mean field analysis of multi population neural networks with random synaptic weights and stochastic inputs
- Transition to chaos in random neuronal networks
- A Theory of Solving TAP Equations for Ising Models with General Invariant Random Matrices
- Mean-field theory for a spin-glass model of neural networks: TAP free energy and paramagnetic to spin-glass transition
- The path-integral analysis of an associative memory model storing an infinite number of finite limit cycles
- Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
- Response Functions Improving Performance in Analog Attractor Neural Networks