An online supervised learning method based on gradient descent for spiking neurons
An online supervised learning method based on gradient descent for spiking neurons
复制标题
一种基于梯度下降的尖峰神经元在线监督学习方法
DOI：
10.1016/j.neunet.2017.04.010
复制
发表时间：
2017
期刊：
影响因子：
7.8
通讯作者：
Zhong Shuiming
中科院分区：
文献类型：
--
作者：
Xu Yan;Yang Jing;Zhong Shuiming
对放电神经元进行时间编码的监督学习的目的是使神经元发出特定的放电序列，该序列由准确的放电时间编码。基于梯度下降(GDB)的学习方法在当前的研究中得到了广泛的应用和验证。虽然现有的GDB多脉冲学习(或脉冲序列学习)方法具有较好的性能，但它们以离线的方式工作，仍然存在一些局限性。基于真实生物神经元突触的在线调节机制，提出了一种用于神经元放电的GDB棘波序列在线学习方法。该方法构造误差函数，一旦神经元在其运行过程中发出尖峰信号，就计算突触权重的调整。本文对期望输出尖峰和实际输出尖峰进行分析和综合，以便在权重调整计算中选择合适的输入尖峰。实验结果表明，与离线学习方式相比，该方法明显提高了学习性能，与其他学习方法相比，在学习精度上也有一定优势。较强的学习能力决定了该方法具有较大的模式存储容量。
The purpose of supervised learning with temporal encoding for spiking neurons is to make the neurons emit a specific spike train encoded by precise firing times of spikes. The gradient-descent-based (GDB) learning methods are widely used and verified in the current research. Although the existing GDB multi-spike learning (or spike sequence learning) methods have good performance, they work in an offline manner and still have some limitations. This paper proposes an online GDB spike sequence learning method for spiking neurons that is based on the online adjustment mechanism of real biological neuron synapses. The method constructs error function and calculates the adjustment of synaptic weights as soon as the neurons emit a spike during their running process. We analyze and synthesize desired and actual output spikes to select appropriate input spikes in the calculation of weight adjustment in this paper. The experimental results show that our method obviously improves learning performance compared with the offline learning manner and has certain advantage on learning accuracy compared with other learning methods. Stronger learning ability determines that the method has large pattern storage capacity.