Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916392811364352 |
|---|---|
| author | Duque, Alice Freire, Pedro Manuylovich, Egor Stoliarov, Dmitrii Prilepsky, Jaroslaw Turitsyn, Sergei |
| author_facet | Duque, Alice Freire, Pedro Manuylovich, Egor Stoliarov, Dmitrii Prilepsky, Jaroslaw Turitsyn, Sergei |
| contents | This work tackles the critical challenge of mitigating "hardware noise" in deep analog neural networks, a major obstacle in advancing analog signal processing devices. We propose a comprehensive, hardware-agnostic solution to address both correlated and uncorrelated noise affecting the activation layers of deep neural models. The novelty of our approach lies in its ability to demystify the "black box" nature of noise-resilient networks by revealing the underlying mechanisms that reduce sensitivity to noise. In doing so, we introduce a new explainable regularization framework that harnesses these mechanisms to significantly enhance noise robustness in deep neural architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations Duque, Alice Freire, Pedro Manuylovich, Egor Stoliarov, Dmitrii Prilepsky, Jaroslaw Turitsyn, Sergei Machine Learning Artificial Intelligence Optics This work tackles the critical challenge of mitigating "hardware noise" in deep analog neural networks, a major obstacle in advancing analog signal processing devices. We propose a comprehensive, hardware-agnostic solution to address both correlated and uncorrelated noise affecting the activation layers of deep neural models. The novelty of our approach lies in its ability to demystify the "black box" nature of noise-resilient networks by revealing the underlying mechanisms that reduce sensitivity to noise. In doing so, we introduce a new explainable regularization framework that harnesses these mechanisms to significantly enhance noise robustness in deep neural architectures. |
| title | Improving Analog Neural Network Robustness: A Noise-Agnostic Approach with Explainable Regularizations |
| topic | Machine Learning Artificial Intelligence Optics |
| url | https://arxiv.org/abs/2409.08633 |