SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
Peking University · Peng Cheng Laboratory · +7 more institutions
Abstract
Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties. As the emerging spiking deep learning paradigm attracts increasing interest, traditional programming frameworks cannot meet the demands of the automatic differentiation, parallel computation acceleration, and high integration of processing neuromorphic datasets and deployment. In this work, we present the SpikingJelly framework to address the aforementioned dilemma. We contribute a full-stack toolkit for preprocessing neuromorphic datasets, building deep SNNs, optimizing their parameters, and deploying SNNs on neuromorphic chips.…
Citation impact
- FWCI
- 42.38
- Percentile
- 100%
- References
- 149
Authors
10- WFWei Fang
Peking University, Peng Cheng Laboratory
- YCYanqi Chen
Peking University, Peng Cheng Laboratory
- JDJianhao Ding
Peking University
- ZYZhaofei Yu
Peking University, Beijing Academy of Artificial Intelligence
- TMTimothée Masquelier
Centre National de la Recherche Scientifique, Centre de recherche cerveau et cognition
Topics & keywords
- Neuromorphic engineering
- Spiking neural network
- Computer science
- Spike (software development)
- Artificial intelligence
- Computer architecture
- Artificial neural network
- Flexibility (engineering)