Input-Driven Dynamics for Robust Memory Retrieval in Hopfield Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908361113468928 |
|---|---|
| author | Betteti, Simone Baggio, Giacomo Bullo, Francesco Zampieri, Sandro |
| author_facet | Betteti, Simone Baggio, Giacomo Bullo, Francesco Zampieri, Sandro |
| contents | The Hopfield model provides a mathematically idealized yet insightful framework for understanding the mechanisms of memory storage and retrieval in the human brain. This model has inspired four decades of extensive research on learning and retrieval dynamics, capacity estimates, and sequential transitions among memories. Notably, the role and impact of external inputs has been largely underexplored, from their effects on neural dynamics to how they facilitate effective memory retrieval. To bridge this gap, we propose a novel dynamical system framework in which the external input directly influences the neural synapses and shapes the energy landscape of the Hopfield model. This plasticity-based mechanism provides a clear energetic interpretation of the memory retrieval process and proves effective at correctly classifying highly mixed inputs. Furthermore, we integrate this model within the framework of modern Hopfield architectures, using this connection to elucidate how current and past information are combined during the retrieval process. Finally, we embed both the classic and the new model in an environment disrupted by noise and compare their robustness during memory retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_05849 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Input-Driven Dynamics for Robust Memory Retrieval in Hopfield Networks Betteti, Simone Baggio, Giacomo Bullo, Francesco Zampieri, Sandro Neurons and Cognition Statistical Mechanics Artificial Intelligence Machine Learning Dynamical Systems 37N25 (Primary) 37C75, 34D45 (Secondary) I.5.1; I.2.11 The Hopfield model provides a mathematically idealized yet insightful framework for understanding the mechanisms of memory storage and retrieval in the human brain. This model has inspired four decades of extensive research on learning and retrieval dynamics, capacity estimates, and sequential transitions among memories. Notably, the role and impact of external inputs has been largely underexplored, from their effects on neural dynamics to how they facilitate effective memory retrieval. To bridge this gap, we propose a novel dynamical system framework in which the external input directly influences the neural synapses and shapes the energy landscape of the Hopfield model. This plasticity-based mechanism provides a clear energetic interpretation of the memory retrieval process and proves effective at correctly classifying highly mixed inputs. Furthermore, we integrate this model within the framework of modern Hopfield architectures, using this connection to elucidate how current and past information are combined during the retrieval process. Finally, we embed both the classic and the new model in an environment disrupted by noise and compare their robustness during memory retrieval. |
| title | Input-Driven Dynamics for Robust Memory Retrieval in Hopfield Networks |
| topic | Neurons and Cognition Statistical Mechanics Artificial Intelligence Machine Learning Dynamical Systems 37N25 (Primary) 37C75, 34D45 (Secondary) I.5.1; I.2.11 |
| url | https://arxiv.org/abs/2411.05849 |