Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memories
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929745165287424 |
|---|---|
| author | Alessandrelli, Andrea Barra, Adriano Ladiana, Andrea Lepre, Andrea Ricci-Tersenghi, Federico |
| author_facet | Alessandrelli, Andrea Barra, Adriano Ladiana, Andrea Lepre, Andrea Ricci-Tersenghi, Federico |
| contents | By leveraging tools from the statistical mechanics of complex systems, in these short notes we extend the architecture of a neural network for hetero-associative memory (called three-directional associative memories, TAM) to explore supervised and unsupervised learning protocols. In particular, by providing entropic-heterogeneous datasets to its various layers, we predict and quantify a new emergent phenomenon -- that we term {\em layer's cooperativeness} -- where the interplay of dataset entropies across network's layers enhances their retrieval capabilities Beyond those they would have without reciprocal influence. Naively we would expect layers trained with less informative datasets to develop smaller retrieval regions compared to those pertaining to layers that experienced more information: this does not happen and all the retrieval regions settle to the same amplitude, allowing for optimal retrieval performance globally. This cooperative dynamics marks a significant advancement in understanding emergent computational capabilities within disordered systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04454 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memories Alessandrelli, Andrea Barra, Adriano Ladiana, Andrea Lepre, Andrea Ricci-Tersenghi, Federico Disordered Systems and Neural Networks Machine Learning By leveraging tools from the statistical mechanics of complex systems, in these short notes we extend the architecture of a neural network for hetero-associative memory (called three-directional associative memories, TAM) to explore supervised and unsupervised learning protocols. In particular, by providing entropic-heterogeneous datasets to its various layers, we predict and quantify a new emergent phenomenon -- that we term {\em layer's cooperativeness} -- where the interplay of dataset entropies across network's layers enhances their retrieval capabilities Beyond those they would have without reciprocal influence. Naively we would expect layers trained with less informative datasets to develop smaller retrieval regions compared to those pertaining to layers that experienced more information: this does not happen and all the retrieval regions settle to the same amplitude, allowing for optimal retrieval performance globally. This cooperative dynamics marks a significant advancement in understanding emergent computational capabilities within disordered systems. |
| title | Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memories |
| topic | Disordered Systems and Neural Networks Machine Learning |
| url | https://arxiv.org/abs/2503.04454 |