Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling
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_ | 1866913229006962688 |
|---|---|
| author | Safa, Ali Jaltare, Vikrant Sebt, Samira Gano, Kameron Leugering, Johannes Gielen, Georges Cauwenberghs, Gert |
| author_facet | Safa, Ali Jaltare, Vikrant Sebt, Samira Gano, Kameron Leugering, Johannes Gielen, Georges Cauwenberghs, Gert |
| contents | This paper studies the use of Metropolis-Hastings sampling for training Spiking Neural Network (SNN) hardware subject to strong unknown non-idealities, and compares the proposed approach to the common use of the backpropagation of error (backprop) algorithm and surrogate gradients, widely used to train SNNs in literature. Simulations are conducted within a chip-in-the-loop training context, where an SNN subject to unknown distortion must be trained to detect cancer from measurements, within a biomedical application context. Our results show that the proposed approach strongly outperforms the use of backprop by up to $27\%$ higher accuracy when subject to strong hardware non-idealities. Furthermore, our results also show that the proposed approach outperforms backprop in terms of SNN generalization, needing $>10 \times$ less training data for achieving effective accuracy. These findings make the proposed training approach well-suited for SNN implementations in analog subthreshold circuits and other emerging technologies where unknown hardware non-idealities can jeopardize backprop. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling Safa, Ali Jaltare, Vikrant Sebt, Samira Gano, Kameron Leugering, Johannes Gielen, Georges Cauwenberghs, Gert Neural and Evolutionary Computing Computer Vision and Pattern Recognition This paper studies the use of Metropolis-Hastings sampling for training Spiking Neural Network (SNN) hardware subject to strong unknown non-idealities, and compares the proposed approach to the common use of the backpropagation of error (backprop) algorithm and surrogate gradients, widely used to train SNNs in literature. Simulations are conducted within a chip-in-the-loop training context, where an SNN subject to unknown distortion must be trained to detect cancer from measurements, within a biomedical application context. Our results show that the proposed approach strongly outperforms the use of backprop by up to $27\%$ higher accuracy when subject to strong hardware non-idealities. Furthermore, our results also show that the proposed approach outperforms backprop in terms of SNN generalization, needing $>10 \times$ less training data for achieving effective accuracy. These findings make the proposed training approach well-suited for SNN implementations in analog subthreshold circuits and other emerging technologies where unknown hardware non-idealities can jeopardize backprop. |
| title | Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling |
| topic | Neural and Evolutionary Computing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.06284 |