A generalized Hopfield model to store and retrieve mismatched memory patterns
arXiv:2204.04520 · doi:10.1088/1742-5468/ac7e40
Abstract
We study a class of Hopfield models where the memories are represented by a mixture of Gaussian and binary variables and the neurons are Ising spins. We study the properties of this family of models as the relative weight of the two kinds of variables in the patterns varies. We quantitatively determine how the retrieval phase squeezes towards zero as the memory patterns contain a larger fraction of mismatched variables. As the memory is purely Gaussian retrieval is lost for any positive storage capacity. It is shown that this comes about because of the spherical symmetry of the free energy in the Gaussian case. Introducing two different memory pattern overlaps between spin configurations and each contribution to the pattern from the two kinds of variables one can observe that the Gaussian parts of the patterns act as a noise, making retrieval more difficult. The basins of attraction of the states, the accuracy of the retrieval and the storage capacity are studied by means of Monte Carlo numerical simulations. We uncover that even in the limit where the network capacity shrinks to zero, the (few) retrieval states maintain a large basin of attraction and large overlaps with the mismatched patterns. So the network can be used for retrieval, but with a very small capacity.
arXiv comment18 pages, 27 figures
References in corpus (10)
- Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
- Hopfield Networks is All You Need
- Phase transitions in Restricted Boltzmann Machines with generic priors
- Replica Symmetry Breaking in Attractor Neural Network Models
- Optical computation of a spin glass dynamics with tunable complexity
- Stochastic symmetry-breaking in a gaussian Hopfield model
- Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
- Infinitely many states and stochastic symmetry in a Gaussian Potts-Hopfield model
- Recurrent neural networks that generalize from examples and optimize by dreaming
- Dreaming neural networks: forgetting spurious memories and reinforcing pure ones