Supervised Learning in Multilayer Spiking Neural Networks With Spike Temporal Error Backpropagation
Supervised Learning in Multilayer Spiking Neural Networks With Spike Temporal Error Backpropagation
复制标题
DOI：
10.1109/tnnls.2022.3164930
复制
发表时间：
2022-04-18
影响因子：
10.4
通讯作者：
Zhang, Malu
中科院分区：
文献类型：
--
作者：
Luo, Xiaoling;Qu, Hong;Zhang, Malu
脑激发脉冲神经网络具有功耗低、计算能力强等优点。然而，缺乏有效的学习算法阻碍了snn的理论发展和应用。现有的snn学习算法大多基于突触权值调整。然而，神经科学的研究结果证实，突触延迟也可以被调节，在学习过程中发挥重要作用。本文提出了一种基于梯度下降的突触延迟学习算法，以提高单个尖峰神经元的顺序学习性能。此外，我们将所提出的方法扩展到具有尖峰时间误差反向传播的多层snn。在所提出的多层学习算法中，信息被编码在单个神经元尖峰的相对时间中，并且学习是基于突触后尖峰时间相对于突触前尖峰时间的精确导数进行的。在合成数据集和真实数据集上的实验结果表明，与现有的基于峰值时间的学习算法相比，学习效率和准确性都有显著提高。我们还在基于snn的视听模式识别多模态计算模型中对所提出的学习方法进行了评估，与同类方法相比，该方法取得了更好的性能。
The brain-inspired spiking neural networks (SNNs) hold the advantages of lower power consumption and powerful computing capability. However, the lack of effective learning algorithms has obstructed the theoretical advance and applications of SNNs. The majority of the existing learning algorithms for SNNs are based on the synaptic weight adjustment. However, neuroscience findings confirm that synaptic delays can also be modulated to play an important role in the learning process. Here, we propose a gradient descent-based learning algorithm for synaptic delays to enhance the sequential learning performance of single spiking neuron. Moreover, we extend the proposed method to multilayer SNNs with spike temporal-based error backpropagation. In the proposed multilayer learning algorithm, information is encoded in the relative timing of individual neuronal spikes, and learning is performed based on the exact derivatives of the postsynaptic spike times with respect to presynaptic spike times. Experimental results on both synthetic and realistic datasets show significant improvements in learning efficiency and accuracy over the existing spike temporal-based learning algorithms. We also evaluate the proposed learning method in an SNN-based multimodal computational model for audiovisual pattern recognition, and it achieves better performance compared with its counterparts.