Recognition Capabilities of a Hopfield Model with Auxiliary Hidden Neurons

Abstract

We study the recognition capabilities of the Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. We show that the recognition capabilities of such a model at zero-temperature outperform those of the original Hopfield model, due to a substantial increase of the storage capacity and the lack of a naturally defined basin of attraction. The modified model does not fall abruptly in a regime of complete confusion when memory load exceeds a sharp threshold.

References in corpus (9)

• Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
• Scaling corrections: site-percolation and Ising model in three dimensions
• Efficient supervised learning in networks with binary synapses
• Finite-Size Scaling at $\xi /L\gg 1$
• Mean-field message-passing equations in the Hopfield model and its generalizations
• Shaping the learning landscape in neural networks around wide flat minima
• From Dyson to Hopfield: Processing on hierarchical networks
• On the role of synaptic stochasticity in training low-precision neural networks
• Efficiency of local learning rules in threshold-linear associative networks

Cited by in corpus (1)

• Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks