Low-Power Real-Time Sequential Processing with Spiking Neural Networks
Low-Power Real-Time Sequential Processing with Spiking Neural Networks
复制标题
DOI：
10.1109/iscas46773.2023.10181703
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
C. Liyanagedera;M. Nagaraj;Wachirawit Ponghiran;K. Roy
中科院分区：
文献类型：
--
作者：
C. Liyanagedera;M. Nagaraj;Wachirawit Ponghiran;K. Roy
生物大脑能够以令人难以置信的效率处理时间信息。即使拥有现代计算资源，传统的基于学习的方法也难以与其性能相匹配。 “模仿”大脑中生物神经网络的某些功能的尖峰神经网络是解决高计算效率的顺序学习问题的有前途的途径。尽管如此，训练此类网络仍然是一项具有挑战性的任务，因为传统的学习规则并不直接适用于这些仿生神经网络。最近的努力集中在新颖的训练范例上，这些范例允许尖峰神经网络学习输入之间的时间相关性并解决音频或视频处理等顺序任务。这样的成功推动了事件驱动的神经形态硬件的发展，该硬件专门针对尖峰神经网络的节能实现进行了优化。本文重点介绍了用于低功耗实时顺序处理的尖峰神经网络的持续发展，以及通过了解信息流来改进其训练的潜力。
The biological brain is capable of processing temporal information at an incredible efficiency. Even with modern computing resources, traditional learning-based approaches are struggling to match its performance. Spiking neural networks that “mimic” certain functionalities of the biological neural networks in the brain is a promising avenue for solving sequential learning problems with high computational efficiency. Nonetheless, training such networks still remains a challenging task as conventional learning rules are not directly applicable to these bio-inspired neural networks. Recent efforts have focused on novel training paradigms that allow spiking neural networks to learn temporal correlations between inputs and solve sequential tasks such as audio or video processing. Such success has fueled the development of event-driven neuromorphic hardware that is specifically optimized for energy-efficient implementation of spiking neural networks. This paper highlights the ongoing development of spiking neural networks for low-power real-time sequential processing and the potential to improve their training through an understanding of the information flow.