Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910614430941184 |
|---|---|
| author | Chicchi, Lorenzo Fanelli, Duccio Febbe, Diego Buffoni, Lorenzo Di Patti, Francesca Giambagli, Lorenzo Marino, Raffele |
| author_facet | Chicchi, Lorenzo Fanelli, Duccio Febbe, Diego Buffoni, Lorenzo Di Patti, Francesca Giambagli, Lorenzo Marino, Raffele |
| contents | The Continuous-Variable Firing Rate (CVFR) model, widely used in neuroscience to describe the intertangled dynamics of excitatory biological neurons, is here trained and tested as a veritable dynamically assisted classifier. To this end the model is supplied with a set of planted attractors which are self-consistently embedded in the inter-nodes coupling matrix, via its spectral decomposition. Learning to classify amounts to sculp the basin of attraction of the imposed equilibria, directing different items towards the corresponding destination target, which reflects the class of respective pertinence. A stochastic variant of the CVFR model is also studied and found to be robust to aversarial random attacks, which corrupt the items to be classified. This remarkable finding is one of the very many surprising effects which arise when noise and dynamical attributes are made to mutually resonate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13470 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise Chicchi, Lorenzo Fanelli, Duccio Febbe, Diego Buffoni, Lorenzo Di Patti, Francesca Giambagli, Lorenzo Marino, Raffele Machine Learning Disordered Systems and Neural Networks Statistical Mechanics Artificial Intelligence The Continuous-Variable Firing Rate (CVFR) model, widely used in neuroscience to describe the intertangled dynamics of excitatory biological neurons, is here trained and tested as a veritable dynamically assisted classifier. To this end the model is supplied with a set of planted attractors which are self-consistently embedded in the inter-nodes coupling matrix, via its spectral decomposition. Learning to classify amounts to sculp the basin of attraction of the imposed equilibria, directing different items towards the corresponding destination target, which reflects the class of respective pertinence. A stochastic variant of the CVFR model is also studied and found to be robust to aversarial random attacks, which corrupt the items to be classified. This remarkable finding is one of the very many surprising effects which arise when noise and dynamical attributes are made to mutually resonate. |
| title | Deterministic versus stochastic dynamical classifiers: opposing random adversarial attacks with noise |
| topic | Machine Learning Disordered Systems and Neural Networks Statistical Mechanics Artificial Intelligence |
| url | https://arxiv.org/abs/2409.13470 |