STDP-based Unsupervised Feature Learning using Convolution-over-time in Spiking Neural Networks for Energy-Efficient Neuromorphic Computing

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS

Article

Srinivasan, Gopalakrishnan¹  Panda, Priyadarshini¹  Roy, Kaushik¹ 

[1] Purdue Univ, Sch Elect & Comp Engn, 465 Northwestern Ave, W Lafayette, IN 47907 USA.

关键词: Convolutional spiking neural network;    convolution-over-time;    stdp;    unsupervised feature learning;    energy-efficient neuromorphic computing;   

DOI  :  10.1145/3266229

来源: SCIE

【 摘 要 】

Brain-inspired learning models attempt to mimic the computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we propose Spike Timing Dependent Plasticity-based unsupervised feature learning using convolution-over-time in Spiking Neural Network (SNN). We use shared weight kernels that are convolved with the input patterns over time to encode representative input features, thereby improving the sparsity as well as the robustness of the learning model. We show that the Convolutional SNN self-learns several visual categories for object recognition with limited number of training patterns while yielding comparable classification accuracy relative to the fully connected SNN. Further, we quantify the energy benefits of the Convolutional SNN over fully connected SNN on neuromorphic hardware implementation.

【 授权许可】

Free