论文标题
深SNN中最大化操作的尖峰近似
Spiking Approximations of the MaxPooling Operation in Deep SNNs
论文作者
论文摘要
尖峰神经网络（SNN）是生物学启发的神经网络的新兴领域，对低功率AI表现出了希望。存在许多用于构建深SNN的方法，具有人工神经网络（ANN）至SNN转换非常成功。卷积神经网络（CNN）中的MaxPool层是将中间特征映射下样本并引入翻译不变性的组成部分，但是缺乏其硬件友好的尖峰等效限制了此类CNNS转换为深SNNS。在本文中，我们提出了两种适合硬件的方法，可以在深SNN中实现最大值，从而促进了CNN的易于转换，将Maxpool层带到SNNS。首先，我们还在Intel的Loihi神经形态硬件（带有MNIST，FMNIST和CIFAR10 DATASET）上执行使用SPIKING-MAXPool层的SNN；因此，显示了我们方法的可行性。
Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversion being highly successful. MaxPooling layers in Convolutional Neural Networks (CNNs) are an integral component to downsample the intermediate feature maps and introduce translational invariance, but the absence of their hardware-friendly spiking equivalents limits such CNNs' conversion to deep SNNs. In this paper, we present two hardware-friendly methods to implement Max-Pooling in deep SNNs, thus facilitating easy conversion of CNNs with MaxPooling layers to SNNs. In a first, we also execute SNNs with spiking-MaxPooling layers on Intel's Loihi neuromorphic hardware (with MNIST, FMNIST, & CIFAR10 dataset); thus, showing the feasibility of our approach.
