Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2404.05807 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914744954257408 |
|---|---|
| author | Summe, Thomas M. Joshi, Siddharth |
| author_facet | Summe, Thomas M. Joshi, Siddharth |
| contents | Recent advances to algorithms for training spiking neural networks (SNNs) often leverage their unique dynamics. While backpropagation through time (BPTT) with surrogate gradients dominate the field, a rich landscape of alternatives can situate algorithms across various points in the performance, bio-plausibility, and complexity landscape. Evaluating and comparing algorithms is currently a cumbersome and error-prone process, requiring them to be repeatedly re-implemented. We introduce Slax, a JAX-based library designed to accelerate SNN algorithm design, compatible with the broader JAX and Flax ecosystem. Slax provides optimized implementations of diverse training algorithms, allowing direct performance comparison. Its toolkit includes methods to visualize and debug algorithms through loss landscapes, gradient similarities, and other metrics of model behavior during training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_05807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks Summe, Thomas M. Joshi, Siddharth Neural and Evolutionary Computing Recent advances to algorithms for training spiking neural networks (SNNs) often leverage their unique dynamics. While backpropagation through time (BPTT) with surrogate gradients dominate the field, a rich landscape of alternatives can situate algorithms across various points in the performance, bio-plausibility, and complexity landscape. Evaluating and comparing algorithms is currently a cumbersome and error-prone process, requiring them to be repeatedly re-implemented. We introduce Slax, a JAX-based library designed to accelerate SNN algorithm design, compatible with the broader JAX and Flax ecosystem. Slax provides optimized implementations of diverse training algorithms, allowing direct performance comparison. Its toolkit includes methods to visualize and debug algorithms through loss landscapes, gradient similarities, and other metrics of model behavior during training. |
| title | Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2404.05807 |