Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914638547910656 |
|---|---|
| author | Suetake, Kazuma Ushimaru, Takuya Saiin, Ryuji Sawada, Yoshihide |
| author_facet | Suetake, Kazuma Ushimaru, Takuya Saiin, Ryuji Sawada, Yoshihide |
| contents | Spiking neural networks (SNNs) are energy-efficient neural networks because of their spiking nature. However, as the spike firing rate of SNNs increases, the energy consumption does as well, and thus, the advantage of SNNs diminishes. Here, we tackle this problem by introducing a novel penalty term for the spiking activity into the objective function in the training phase. Our method is designed so as to optimize the energy consumption metric directly without modifying the network architecture. Therefore, the proposed method can reduce the energy consumption more than other methods while maintaining the accuracy. We conducted experiments for image classification tasks, and the results indicate the effectiveness of the proposed method, which mitigates the dilemma of the energy--accuracy trade-off. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_01500 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks Suetake, Kazuma Ushimaru, Takuya Saiin, Ryuji Sawada, Yoshihide Machine Learning Neural and Evolutionary Computing Spiking neural networks (SNNs) are energy-efficient neural networks because of their spiking nature. However, as the spike firing rate of SNNs increases, the energy consumption does as well, and thus, the advantage of SNNs diminishes. Here, we tackle this problem by introducing a novel penalty term for the spiking activity into the objective function in the training phase. Our method is designed so as to optimize the energy consumption metric directly without modifying the network architecture. Therefore, the proposed method can reduce the energy consumption more than other methods while maintaining the accuracy. We conducted experiments for image classification tasks, and the results indicate the effectiveness of the proposed method, which mitigates the dilemma of the energy--accuracy trade-off. |
| title | Spiking Synaptic Penalty: Appropriate Penalty Term for Energy-Efficient Spiking Neural Networks |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2302.01500 |