Benchmarking Spiking Neural Network Learning Methods with Varying Locality
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913917849042944 |
|---|---|
| author | Lin, Jiaqi Lu, Sen Bal, Malyaban Sengupta, Abhronil |
| author_facet | Lin, Jiaqi Lu, Sen Bal, Malyaban Sengupta, Abhronil |
| contents | Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have been shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within SNNs in an event-based mechanism that significantly reduces energy consumption. However, training SNNs is challenging due to the non-differentiable nature of the spiking mechanism. Traditional approaches, such as Backpropagation Through Time (BPTT), have shown effectiveness but come with additional computational and memory costs and are biologically implausible. In contrast, recent works propose alternative learning methods with varying degrees of locality, demonstrating success in classification tasks. In this work, we show that these methods share similarities during the training process, while they present a trade-off between biological plausibility and performance. Further, given the implicitly recurrent nature of SNNs, this research investigates the influence of the addition of explicit recurrence to SNNs. We experimentally prove that the addition of explicit recurrent weights enhances the robustness of SNNs. We also investigate the performance of local learning methods under gradient and non-gradient-based adversarial attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01782 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Benchmarking Spiking Neural Network Learning Methods with Varying Locality Lin, Jiaqi Lu, Sen Bal, Malyaban Sengupta, Abhronil Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have been shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within SNNs in an event-based mechanism that significantly reduces energy consumption. However, training SNNs is challenging due to the non-differentiable nature of the spiking mechanism. Traditional approaches, such as Backpropagation Through Time (BPTT), have shown effectiveness but come with additional computational and memory costs and are biologically implausible. In contrast, recent works propose alternative learning methods with varying degrees of locality, demonstrating success in classification tasks. In this work, we show that these methods share similarities during the training process, while they present a trade-off between biological plausibility and performance. Further, given the implicitly recurrent nature of SNNs, this research investigates the influence of the addition of explicit recurrence to SNNs. We experimentally prove that the addition of explicit recurrent weights enhances the robustness of SNNs. We also investigate the performance of local learning methods under gradient and non-gradient-based adversarial attacks. |
| title | Benchmarking Spiking Neural Network Learning Methods with Varying Locality |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.01782 |