Noise-Aware Training of Neuromorphic Dynamic Device Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910673694359552 |
|---|---|
| author | Manneschi, Luca Vidamour, Ian T. Stenning, Kilian D. Swindells, Charles Venkat, Guru Griffin, David Gui, Lai Sonawala, Daanish Donskikh, Denis Hariga, Dana Stepney, Susan Branford, Will R. Gartside, Jack C. Hayward, Thomas Ellis, Matthew O. A. Vasilaki, Eleni |
| author_facet | Manneschi, Luca Vidamour, Ian T. Stenning, Kilian D. Swindells, Charles Venkat, Guru Griffin, David Gui, Lai Sonawala, Daanish Donskikh, Denis Hariga, Dana Stepney, Susan Branford, Will R. Gartside, Jack C. Hayward, Thomas Ellis, Matthew O. A. Vasilaki, Eleni |
| contents | Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data processing capabilities, networks of interconnected devices can perform more complex and varied tasks. However, designing networks to perform dynamic tasks is challenging without physical models and accurate quantification of device noise. We propose a novel, noise-aware methodology for training device networks using Neural Stochastic Differential Equations (Neural-SDEs) as differentiable digital twins, accurately capturing the dynamics and associated stochasticity of devices with intrinsic memory. Our approach employs backpropagation through time and cascade learning, allowing networks to effectively exploit the temporal properties of physical devices. We validate our method on diverse networks of spintronic devices across temporal classification and regression benchmarks. By decoupling the training of individual device models from network training, our method reduces the required training data and provides a robust framework for programming dynamical devices without relying on analytical descriptions of their dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07387 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Noise-Aware Training of Neuromorphic Dynamic Device Networks Manneschi, Luca Vidamour, Ian T. Stenning, Kilian D. Swindells, Charles Venkat, Guru Griffin, David Gui, Lai Sonawala, Daanish Donskikh, Denis Hariga, Dana Stepney, Susan Branford, Will R. Gartside, Jack C. Hayward, Thomas Ellis, Matthew O. A. Vasilaki, Eleni Machine Learning Artificial Intelligence Emerging Technologies Neural and Evolutionary Computing Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data processing capabilities, networks of interconnected devices can perform more complex and varied tasks. However, designing networks to perform dynamic tasks is challenging without physical models and accurate quantification of device noise. We propose a novel, noise-aware methodology for training device networks using Neural Stochastic Differential Equations (Neural-SDEs) as differentiable digital twins, accurately capturing the dynamics and associated stochasticity of devices with intrinsic memory. Our approach employs backpropagation through time and cascade learning, allowing networks to effectively exploit the temporal properties of physical devices. We validate our method on diverse networks of spintronic devices across temporal classification and regression benchmarks. By decoupling the training of individual device models from network training, our method reduces the required training data and provides a robust framework for programming dynamical devices without relying on analytical descriptions of their dynamics. |
| title | Noise-Aware Training of Neuromorphic Dynamic Device Networks |
| topic | Machine Learning Artificial Intelligence Emerging Technologies Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2401.07387 |