.png){kind=icon}
返回
Brain-Inspired Learning on Neuromorphic Substrates
.png){kind=icon}
OA
AI
DOI：10.1109/JPROC.2020.3045625.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Neuromorphic hardware strives to emulate brain-like neural networks and thus holds the promise for scalable, low-power information processing on temporal data streams. Yet, to solve real-world problems, these networks need to be trained. However, training on neuromorphic substrates creates significant challenges due to the offline character and the required nonlocal computations of gradient-based learning algorithms. This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates. Specifically, we show a direct connection between real-time recurrent learning (RTRL), an online algorithm for computing gradients in conventional recurrent neural networks (RNNs), and biologically plausible learning rules for training spiking neural networks (SNNs). Furthermore, we motivate a sparse approximation based on block-diagonal Jacobians, which reduces the algorithm's computational complexity, diminishes the nonlocal information requirements, and empirically leads to good learning performance, thereby improving its applicability to neuromorphic substrates. In summary, our framework bridges the gap between synaptic plasticity and gradient-based approaches from deep learning and lays the foundations for powerful information processing on future neuromorphic hardware systems.
Keyword:
Neurons
Biological neural networks
Recurrent neural networks
Substrates
Biology
Synapses
Jacobian matrices
Artificial neural networks
biological neural networks
learning systems
machine learning
neural network hardware
neuromorphic engineering
recurrent neural networks (RNNs)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
25.9
论文数:
9.9K
被引数:
4.5W
机构
引用论文
Diverse synaptic plasticity mechanisms orchestrated to form and retrieve memories in spiking neural networks.png)
NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容