Improved Robustness and Hyperparameter Selection in the Dense Associative Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: McAlister, Hayden, Robins, Anthony, Szymanski, Lech
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912038981206016
author McAlister, Hayden
Robins, Anthony
Szymanski, Lech
author_facet McAlister, Hayden
Robins, Anthony
Szymanski, Lech
contents The Dense Associative Memory generalizes the Hopfield network by allowing for sharper interaction functions. This increases the capacity of the network as an autoassociative memory as nearby learned attractors will not interfere with one another. However, the implementation of the network relies on applying large exponents to the dot product of memory vectors and probe vectors. If the dimension of the data is large the calculation can be very large and result in imprecisions and overflow when using floating point numbers in a practical implementation. We describe the computational issues in detail, modify the original network description to mitigate the problem, and show the modification will not alter the networks' dynamics during update or training. We also show our modification greatly improves hyperparameter selection for the Dense Associative Memory, removing dependence on the interaction vertex and resulting in an optimal region of hyperparameters that does not significantly change with the interaction vertex as it does in the original network.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08742
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improved Robustness and Hyperparameter Selection in the Dense Associative Memory
McAlister, Hayden
Robins, Anthony
Szymanski, Lech
Neural and Evolutionary Computing
Machine Learning
The Dense Associative Memory generalizes the Hopfield network by allowing for sharper interaction functions. This increases the capacity of the network as an autoassociative memory as nearby learned attractors will not interfere with one another. However, the implementation of the network relies on applying large exponents to the dot product of memory vectors and probe vectors. If the dimension of the data is large the calculation can be very large and result in imprecisions and overflow when using floating point numbers in a practical implementation. We describe the computational issues in detail, modify the original network description to mitigate the problem, and show the modification will not alter the networks' dynamics during update or training. We also show our modification greatly improves hyperparameter selection for the Dense Associative Memory, removing dependence on the interaction vertex and resulting in an optimal region of hyperparameters that does not significantly change with the interaction vertex as it does in the original network.
title Improved Robustness and Hyperparameter Selection in the Dense Associative Memory
topic Neural and Evolutionary Computing
Machine Learning
url https://arxiv.org/abs/2407.08742