The Interconnection Tensor Rank and the Neural Network Storage Capacity
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917980696215552 |
|---|---|
| author | Kryzhanovsky, Boris V. |
| author_facet | Kryzhanovsky, Boris V. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05926 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Interconnection Tensor Rank and the Neural Network Storage Capacity Kryzhanovsky, Boris V. Disordered Systems and Neural Networks 94-10 I.5.1 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. |
| title | The Interconnection Tensor Rank and the Neural Network Storage Capacity |
| topic | Disordered Systems and Neural Networks 94-10 I.5.1 |
| url | https://arxiv.org/abs/2504.05926 |