Transfer Learning Algorithm and Software Framework Based on Spiking Neuron Network

• Published in: Jisuanji gongcheng
• Main Author: SHANG Yingjie, DONG Liya, HE Hu
• Format: Article
• Language: English
• Published: Editorial Office of Computer Engineering 2020-03-01
• Subjects: spiking neuron network(snn)|transfer learning|back propagation|multilayer network|mnist dataset|cifar-10 dataset|low power consumption
• Online Access: https://www.ecice06.com/fileup/1000-3428/PDF/20200308.pdf

Spiking Neuron Network(SNN) uses spike sequence for data processing,so it has the excellent characteristic of low power consumption.However,due to the immaturity of learning algorithm,the multilayer network training has difficulty in convergence.Utilizing the mature learning algorithm and fast training speed of the back propagation network,this paper proposes a transfer learning algorithm.The algorithm completes the training process based on the back propagation network and transfers the training results to the spiking neuron networks through the spike coding rules and the adaptive weight mapping relationship.Experimental results show that the transfer learning algorithm can effectively solve the convergence problem in the training process of multilayer spiking neuron networks.The recognition accuracy on the MNIST dataset and CIFAR-10 dataset can be up to 98.56% and 56.00% respectively,with low power consumption at the microwatt level.