The Interconnection Tensor Rank and the Neural Network Storage Capacity
Disordered Systems and Neural Networks
2025-04-09 v1
Abstract
Neural network properties are considered in the case of the interconnection tensor rank being higher than two. This sort of interconnection tensor occurs in realization of crossbar-based neural networks. It is intrinsic for a crossbar design to suffer from parasitic currents. It is shown that the interconnection tensor of a certain form makes the neural network much more efficient: the storage capacity and basin of attraction of the network increase considerably. A network like the Hopfield one is used in the study.
Keywords
Cite
@article{arxiv.2504.05926,
title = {The Interconnection Tensor Rank and the Neural Network Storage Capacity},
author = {Boris V. Kryzhanovsky},
journal= {arXiv preprint arXiv:2504.05926},
year = {2025}
}
Comments
8 pages, 2 figures