Robust exponential binary pattern storage in Little-Hopfield networks
| Title: | Robust exponential binary pattern storage in Little-Hopfield networks |
|---|---|
| Authors: | Hillar, Christopher, Tran, Ngoc, Koepsell, Kilian |
| Publication Year: | 2012 |
| Collection: | Mathematics Quantitative Biology |
| Subject Terms: | Quantitative Biology - Neurons and Cognition, Mathematics - Combinatorics, Mathematics - Dynamical Systems |
| More Details: | The Little-Hopfield network is an auto-associative computational model of neural memory storage and retrieval. This model is known to robustly store collections of randomly generated binary patterns as stable-states of the network dynamics. However, the number of binary memories so storable scales linearly in the number of neurons, and it has been a long-standing open problem whether robust exponential storage of binary patterns was possible in such a network memory model. In this note, we design simple families of Little-Hopfield networks that provably solve this problem affirmatively. As a byproduct, we produce a set of novel (nonlinear) binary codes with an efficient, highly parallelizable denoising mechanism. Comment: This paper has been withdrawn by the authors. preliminary early draft unsuitable for viewing and attribution, instead, see: arXiv:1411.4625 |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/1206.2081 |
| Accession Number: | edsarx.1206.2081 |
| Database: | arXiv |
| Description not available. |