English

Recognition Capabilities of a Hopfield Model with Auxiliary Hidden Neurons

Disordered Systems and Neural Networks 2021-06-16 v1 Statistical Mechanics Biological Physics Neurons and Cognition

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.

Keywords

Cite

@article{arxiv.2101.05247,
  title  = {Recognition Capabilities of a Hopfield Model with Auxiliary Hidden Neurons},
  author = {Marco Benedetti and Victor Dotsenko and Giulia Fischetti and Enzo Marinari and Gleb Oshanin},
  journal= {arXiv preprint arXiv:2101.05247},
  year   = {2021}
}