Electrophysiological studies have shown that mammalian primary visual cortex are selective for the orientations of visual stimuli. Inspired by this mechanism, we propose a hierarchical spiking neural network (SNN) for image classification. Grayscale input images are fed through a feed-forward network consisting of orientation-selective neurons, which then projected to a layer of downstream classifier neurons through the spiking-based supervised tempotron learning rule. Based on the orientation-selective mechanism of the visual cortex and tempotron learning rule, the network can effectively classify images of the extensively studied MNIST database of handwritten digits, which achieves classification accuracy based on only training samples (traditional training set is ). Compared with other classification methods, our model not only guarantees the biological plausibility and the accuracy of image classification but also significantly reduces the needed training samples. Considering the fact that the most commonly used deep learning neural networks need big data samples and high power consumption in image recognition, this brain-inspired computational neural network model based on the layer-by-layer hierarchical image processing mechanism of the visual cortex may provide a basis for the wide application of spiking neural networks in the field of intelligent computing.

中文翻译：

---

基于视觉机制和监督突触学习的脉冲神经网络模式识别

电生理学研究表明，哺乳动物初级视觉皮层对视觉刺激的方向具有选择性。受这种机制的启发，我们提出了一种用于图像分类的分层尖峰神经网络（SNN）。灰度输入图像通过一个由方向选择神经元组成的前馈网络馈送，然后通过基于尖峰的有监督的 tempotron 学习规则投影到下游分类器神经元层。该网络基于视觉皮层的方向选择机制和节拍器学习规则，可以有效地对广泛研究的手写数字 MNIST 数据库的图像进行分类，实现仅基于训练样本（传统训练集为）的分类精度。与其他分类方法相比，我们的模型不仅保证了图像分类的生物学合理性和准确性，而且显着减少了所需的训练样本。考虑到最常用的深度学习神经网络在图像识别中需要大数据样本和高功耗，这种基于视觉皮层逐层分层图像处理机制的类脑计算神经网络模型可能提供为尖峰神经网络在智能计算领域的广泛应用奠定了基础。