Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.02013 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912257623982080 |
|---|---|
| author | Fono, Adalbert Singh, Manjot Araya, Ernesto Petersen, Philipp C. Boche, Holger Kutyniok, Gitta |
| author_facet | Fono, Adalbert Singh, Manjot Araya, Ernesto Petersen, Philipp C. Boche, Holger Kutyniok, Gitta |
| contents | Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons, offer a promising alternative with potential computational and energy-efficiency gains. This article examines the computational properties of spiking networks through the lens of learning theory, focusing on expressivity, training, and generalization, as well as energy-efficient implementations while comparing them to artificial neural networks. By categorizing spiking models based on time representation and information encoding, we highlight their strengths, challenges, and potential as an alternative computational paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sustainable AI: Mathematical Foundations of Spiking Neural Networks Fono, Adalbert Singh, Manjot Araya, Ernesto Petersen, Philipp C. Boche, Holger Kutyniok, Gitta Neural and Evolutionary Computing Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons, offer a promising alternative with potential computational and energy-efficiency gains. This article examines the computational properties of spiking networks through the lens of learning theory, focusing on expressivity, training, and generalization, as well as energy-efficient implementations while comparing them to artificial neural networks. By categorizing spiking models based on time representation and information encoding, we highlight their strengths, challenges, and potential as an alternative computational paradigm. |
| title | Sustainable AI: Mathematical Foundations of Spiking Neural Networks |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2503.02013 |