期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 33, 期 7, 页码 2744-2757出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2020.3044364
关键词
Benchmark testing; Task analysis; Biological neural networks; Training; Licenses; Encoding; Voltage control; Audio; benchmark; classification; data set; neuromorphic computing; spiking neural networks; spoken digits; surrogate gradients
类别
资金
- European Union [604102, 269921, 243914]
- Novartis Research Foundation
- state of Baden-Wurttemberg through bwHPC
- German Research Foundation (DFG) [INST 39/963-1 FUGG]
- Horizon 2020 Framework Program [720270, 785907, 945539]
Spiking neural networks serve as the basis for versatile and power-efficient information processing in the brain, and optimization techniques allow for complex functional networks to be instantiated in-silico. To compare the computational performance of these networks, spike-based classification data sets have been introduced, highlighting the importance of utilizing spike timing information for accurate classification.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据