Jointly Learning Network Connections and Link Weights in Spiking Neural Networks
Jointly Learning Network Connections and Link Weights in Spiking Neural Networks
Yu Qi, Jiangrong Shen, Yueming Wang, Huajin Tang, Hang Yu, Zhaohui Wu, Gang Pan
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 1597-1603.
https://doi.org/10.24963/ijcai.2018/221
Spiking neural networks (SNNs) are considered to be biologically plausible and power-efficient on neuromorphic hardware. However, unlike the brain mechanisms, most existing SNN algorithms have fixed network topologies and connection relationships. This paper proposes a method to jointly learn network connections and link weights simultaneously. The connection structures are optimized by the spike-timing-dependent plasticity (STDP) rule with timing information, and the link weights are optimized by a supervised algorithm. The connection structures and the weights are learned alternately until a termination condition is satisfied. Experiments are carried out using four benchmark datasets. Our approach outperforms classical learning methods such as STDP, Tempotron, SpikeProp, and a state-of-the-art supervised algorithm. In addition, the learned structures effectively reduce the number of connections by about 24%, thus facilitate the computational efficiency of the network.
Keywords:
Machine Learning: Machine Learning
Machine Learning: Neural Networks
Humans and AI: Cognitive Modeling
Humans and AI: Brain Sciences
Humans and AI: Cognitive Systems