| DOI | Resolve DOI: https://doi.org/10.1145/3546790.3546814 |
|---|
| Author | Search for: Nesbit, Steven C.; Search for: O'Brien, Andrew; Search for: Rego, Jocelyn; Search for: Parpart, Gavin; Search for: Gonzalez, Carlos; Search for: Kenyon, Garrett T.; Search for: Kim, Edward; Search for: Stewart, Terrence C.1; Search for: Watkins, Yijing |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Funder | Search for: NSF (National Science Foundation); Search for: DOE U.S. Department of Energy |
|---|
| Format | Text, Article |
|---|
| Conference | ICONS: International Conference on Neuromorphic Systems, July 27-29, 2022, Knoxville TN USA |
|---|
| Physical description | 8 p. |
|---|
| Subject | neuro-inspired artificial intelligence; machine learning; neuromorphic computing |
|---|
| Abstract | 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. |
|---|
| Publication date | 2022-07-27 |
|---|
| Publisher | ACM |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 4d799a06-3a9e-4c77-9603-7ad0d6d07be3 |
|---|
| Record created | 2022-10-19 |
|---|
| Record modified | 2022-10-21 |
|---|
