模拟卷积神经网络到脉冲卷积网络转换的理论和工具
Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
摘要：
深度卷积神经网络（CNN）已在众多现实世界的机器学习应用中显示出巨大潜力，但在大型CNN中实时执行推理仍然是一个挑战。我们之前已经证明，传统的CNN可以转换为深度尖峰神经网络（SNN），它表现出类似的准确性，同时减少了延迟和计算负载，这是由于它们的数据驱动，基于事件的计算风格。在这里，我们提供了一个新的理论来解释为什么这种转换是成功的，并从中衍生出几个新的工具来将更大，更强大的深度网络转换为SNN。我们确定了以前的转换方法中近似误差的主要来源，并提出了解决这些问题的简单机制。此外，我们开发了常见的CNN操作，如最大池，softmax和批量归一化，它允许几乎无损的任意CNN架构转换到尖峰域的尖峰实现。在MNIST和CIFAR10基准上对不同网络架构进行的经验评估导致了迄今为止报告的最佳SNN结果。
英文摘要：
Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge. We have previously demonstrated that traditional CNNs can be converted into deep spiking neural networks (SNNs), which exhibit similar accuracy while reducing both latency and computational load as a consequence of their data-driven, event-based style of computing. Here we provide a novel theory that explains why this conversion is successful, and derive from it several new tools to convert a larger and more powerful class of deep networks into SNNs. We identify the main sources of approximation errors in previous conversion methods, and propose simple mechanisms to fix these issues. Furthermore, we develop spiking implementations of common CNN operations such as max-pooling, softmax, and batch-normalization, which allow almost loss-less conversion of arbitrary CNN architectures into the spiking domain. Empirical evaluation of different network architectures on the MNIST and CIFAR10 benchmarks leads to the best SNN results reported to date.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
