尖峰神经网络
计算机科学
神经形态工程学
人工智能
人工神经网络
信号处理
钥匙(锁)
领域(数学分析)
机器学习
数字信号处理
计算机硬件
数学
计算机安全
数学分析
作者
Emre Neftci,Hesham Mostafa,Friedemann Zenke
出处
期刊:IEEE Signal Processing Magazine
[Institute of Electrical and Electronics Engineers]
日期:2019-11-01
卷期号:36 (6): 51-63
被引量:519
标识
DOI:10.1109/msp.2019.2931595
摘要
Spiking neural networks (SNNs) are nature's versatile solution to fault-tolerant, energy-efficient signal processing. To translate these benefits into hardware, a growing number of neuromorphic spiking NN processors have attempted to emulate biological NNs. These developments have created an imminent need for methods and tools that enable such systems to solve real-world signal processing problems. Like conventional NNs, SNNs can be trained on real, domain-specific data; however, their training requires the overcoming of a number of challenges linked to their binary and dynamical nature. This article elucidates step-by-step the problems typically encountered when training SNNs and guides the reader through the key concepts of synaptic plasticity and data-driven learning in the spiking setting. Accordingly, it gives an overview of existing approaches and provides an introduction to surrogate gradient (SG) methods, specifically, as a particularly flexible and efficient method to overcome the aforementioned challenges.
科研通智能强力驱动
Strongly Powered by AbleSci AI