| DOI | Trouver le DOI : https://doi.org/10.1145/3546790.3546814 |
|---|
| Auteur | Rechercher : Nesbit, Steven C.; Rechercher : O'Brien, Andrew; Rechercher : Rego, Jocelyn; Rechercher : Parpart, Gavin; Rechercher : Gonzalez, Carlos; Rechercher : Kenyon, Garrett T.; Rechercher : Kim, Edward; Rechercher : Stewart, Terrence C.1; Rechercher : Watkins, Yijing |
|---|
| Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
|---|
| Bailleur de fonds | Rechercher : NSF (National Science Foundation); Rechercher : DOE U.S. Department of Energy |
|---|
| Format | Texte, Article |
|---|
| Conférence | ICONS: International Conference on Neuromorphic Systems, July 27-29, 2022, Knoxville TN USA |
|---|
| Description physique | 8 p. |
|---|
| Sujet | neuro-inspired artificial intelligence; machine learning; neuromorphic computing |
|---|
| Résumé | The state-of-the-art in machine learning has been achieved primarily by deep learning artificial neural networks. These networks are powerful but biologically implausible and energy intensive. In parallel, a new paradigm of neural network is being researched that can alleviate some of the computational and energy issues. These networks, spiking neural networks (SNNs), have transformative potential if the community is able to bridge the gap between deep learning and SNNs. However, SNNs are notoriously difficult to train and lack precision in their communication. In an effort to overcome these limitations and retain the benefits of the learning process in deep learning, we investigate novel ways to translate between them. We construct several network designs with varying degrees of biological plausibility. We then test our designs on an image classification task and demonstrate our designs allow for a customized tradeoff between biological plausibility, power efficiency, inference time, and accuracy. |
|---|
| Date de publication | 2022-07-27 |
|---|
| Maison d’édition | ACM |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 4d799a06-3a9e-4c77-9603-7ad0d6d07be3 |
|---|
| Enregistrement créé | 2022-10-19 |
|---|
| Enregistrement modifié | 2022-10-21 |
|---|
