基于脉冲神经网络的迁移学习算法与软件框架  

Transfer Learning Algorithm and Software Framework Based on Spiking Neuron Network

作　　者：尚瑛杰 董丽亚 何虎[1] SHANG Yingjie;DONG Liya;HE Hu(Department of Microelectronics and Nanoelectronics,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学微电子与纳电子学系,北京100084

出　　处：《计算机工程》2020年第3期53-59,共7页Computer Engineering

基　　金：国家自然科学基金(91846303)。

摘　　要：使用脉冲序列进行数据处理的脉冲神经网络具有优异的低功耗特性,但由于学习算法不成熟,多层网络训练存在收敛困难的问题。利用反向传播网络具有学习算法成熟和训练速度快的特点,设计一种迁移学习算法。基于反向传播网络完成训练过程,并通过脉冲编码规则和自适应的权值映射关系,将训练结果迁移至脉冲神经网络。实验结果表明,在多层脉冲神经网络中,迁移学习算法能够有效解决训练过程中收敛困难的问题,在MNIST数据集和CIFAR-10数据集上的识别准确率分别达到98.56%和56.00%,且具有微瓦级别的低功耗特性。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.

关 键 词：脉冲神经网络 迁移学习 反向传播 多层网络 MNIST数据集 CIFAR-10数据集 低功耗 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]