The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks
The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks
复制标题
DOI：
10.1109/tnnls.2020.3044364
复制
发表时间：
2022-07-01
影响因子：
10.4
通讯作者：
Zenke, Friedemann
中科院分区：
文献类型：
--
作者：
Cramer, Benjamin;Stradmann, Yannik;Zenke, Friedemann
尖峰神经网络是大脑中多功能和节能信息处理的基础。虽然我们目前缺乏对这些网络如何计算的详细了解，但最近开发的优化技术使我们能够在计算机上实例化越来越复杂的功能尖峰神经网络。这些方法有望构建更高效的非冯·诺依曼计算硬件，并将为解开大脑回路功能的探索提供新的前景。为了加速这些方法的发展，客观地比较它们的性能是必不可少的。然而，目前还没有被广泛接受的方法来比较脉冲神经网络的计算性能。为了解决这个问题，我们引入了两个基于尖峰的分类数据集，广泛适用于基准的尖峰神经网络的软件和神经形态硬件实现。为了实现这一点，我们开发了一个通用的音频到尖峰转换程序的灵感来自神经生理学。此外，我们将这种转换应用到现有的和一个新的语音数据集。后者是我们专门为这项研究创建的免费，高保真和单词级对齐的海德堡数字数据集。通过训练一系列传统的和尖峰分类器，我们表明，利用这些数据集内的尖峰定时信息是至关重要的良好的分类精度。这些结果作为第一个参考未来的性能比较的尖峰神经网络。
Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking neural networks in-silico. These methods hold the promise to build more efficient non-von-Neumann computing hardware and will offer new vistas in the quest of unraveling brain circuit function. To accelerate the development of such methods, objective ways to compare their performance are indispensable. Presently, however, there are no widely accepted means for comparing the computational performance of spiking neural networks. To address this issue, we introduce two spike-based classification data sets, broadly applicable to benchmark both software and neuromorphic hardware implementations of spiking neural networks. To accomplish this, we developed a general audio-to-spiking conversion procedure inspired by neurophysiology. Furthermore, we applied this conversion to an existing and a novel speech data set. The latter is the free, high-fidelity, and word-level aligned Heidelberg digit data set that we created specifically for this study. By training a range of conventional and spiking classifiers, we show that leveraging spike timing information within these data sets is essential for good classification accuracy. These results serve as the first reference for future performance comparisons of spiking neural networks.