Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method
Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method
复制标题
通过精确的突触效率调整方法有效训练有监督的尖峰神经网络
DOI：
10.1109/tnnls.2016.2541339
复制
发表时间：
2017-06
影响因子：
10.4
通讯作者：
Hong Qu
中科院分区：
文献类型：
--
作者：
Xiurui Xie;Hong Qu
脉冲神经网络（SNN）是第三代神经网络，在模式识别等认知任务中表现出色。在生物海马体中发现的时间神经编码机制使SNN具备更强的能力。
The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.
登录
查看更多内容
影响因子：
2.9
作者：
Yan Xu;Xiaoqin Zeng;Shuiming Zhong
通讯作者：
Yan Xu;Xiaoqin Zeng;Shuiming Zhong
影响因子：
2.9
作者：
R. V. Rullen;S. Thorpe
通讯作者：
R. V. Rullen;S. Thorpe
DOI：
--
发表时间：
--
期刊：
--
影响因子：
--
作者：
Z. Nadasdy
通讯作者：
Z. Nadasdy
影响因子：
7.8
作者：
Ghosh-Dastidar, Samanwoy;Adeli, Hojjat
通讯作者：
Adeli, Hojjat
DOI：
10.1109/ijcnn.2014.6889847
发表时间：
2014-07
期刊：
2014 International Joint Conference on Neural Networks (IJCNN)
影响因子：
--
作者：
Bernhard A. Kaplan;M. A. Khoei;A. Lansner;Laurent Udo Perrinet
通讯作者：
Bernhard A. Kaplan;M. A. Khoei;A. Lansner;Laurent Udo Perrinet