A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition
A Bio-Inspired Hierarchical Spiking Neural Network With Reward-Modulated STDP Learning Rule for AER Object Recognition
复制标题
具有用于 AER 对象识别的奖励调制 STDP 学习规则的仿生分层尖峰神经网络
作者：
Qian Zhou;Xiaohu Li
固有的基于峰值和事件驱动的计算使得峰值神经网络（snn）自然适合为神经形态视觉处理提供高效、低延迟的解决方案。在这项工作中，我们提出了一个地址事件表示（AER）目标识别系统，该系统由噪声滤波器，事件流分割模块和分层卷积SNN组成。为了提高生物启发的浅层次SNN用于AER目标识别的特征学习能力，我们采用基于R-STDP学习规则和第一尖峰编码的卷积SNN，在基于Gabor滤波器的事件驱动卷积进行初级特征学习后进一步提取特征。R-STDP学习规则通过将局部STDP学习规则与全局奖励信号相结合，使网络能够调整权值，并且在不使用外部分类器的情况下进行分类。实验结果表明，在四种常用的AER数据集上，我们的方法明显优于现有的基于分层snn的识别方法。此外，该方法在使用非常短的输入事件流时具有更好的识别能力，并且可以有效地从小规模的训练集中学习。此外，还提高了网络对输入噪声的鲁棒性。该方法有利于在事件流短、训练样本有限的情况下开发资源受限的神经形态视觉目标识别算法。
The inherent spike-based and event-driven computation makes spiking neural networks (SNNs) naturally suitable to provide efficient and low-latency solution in neuromorphic vision processing. In this work we propose an address-event representation (AER) object recognition system which consists of a noise filter, an event stream segmentation module and a hierarchical convolutional SNN. In order to improve the feature learning capacity of bio-inspired shallow hierarchical SNNs for AER object recognition, we apply a convolutional SNN with R-STDP learning rule and first-spike coding to further extract features after primary feature learning using Gabor filter-based event-driven convolution. The R-STDP learning rule enables the network to adjust weights by combining local STDP learning rule with a global reward signal and to make classification without using an external classifier. Experimental results show that our method significantly outperforms the existing hierarchical SNN-based recognition methods on four popular AER datasets. Moreover, our method has much better recognition ability when using very short input event stream, and can effectively learn from small size training sets. In addition, the robustness of the network to input noise is improved. Our method is very beneficial for developing neuromorphic-vision object recognition algorithm in resource-constrained applications when event streams are short and training samples are limited.