.png){kind=icon}
返回
Binary-Stochasticity-Enabled Highly Efficient Neuromorphic Deep Learning Achieves Better-than-Software Accuracy
.png){kind=icon}
OA
AI
DOI：10.1002/aisy.202300399.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this work, the requirement of using high-precision (HP) signals is lifted and the circuits for implementing deep learning algorithms in memristor-based hardware are simplified. The use of HP signals is required by the backpropagation learning algorithm since the gradient descent learning rule relies on the chain product of partial derivatives. However, it is both challenging and biologically implausible to implement such an HP algorithm in noisy and analog memristor-based hardware systems. Herein, it is demonstrated that the requirement for HP signals handling is not necessary and more efficient deep learning can be achieved when using a binary stochastic learning algorithm. The new algorithm proposed in this work modifies elementary neural network operations, which improves energy efficiency by two orders of magnitude compared to traditional memristor-based hardware and three orders of magnitude compared to complementary metal-oxide-semiconductor-based hardware. It also provides better accuracy in pattern recognition tasks than the HP learning algorithm benchmarks. Herein, a binary stochastic (BS) deep learning algorithm which is both biologically plausible and hardware friendly is proposed. The BS algorithm fully supports online training of memristor-based deep learning and shows better-than-software training and inference accuracy on benchmark tasks. It also improves energy efficiency by more than three orders of magnitude compared with conventional implementations.image (c) 2023 WILEY-VCH GmbH
Keyword:
backpropagation
deep learning
neuromorphic computing
signal binarization
stochastic sampling
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:
6.1
论文数:
2.0K
被引数:
8.4K
机构
引用论文
A memristive deep belief neural network based on silicon synapses基于硅突触的忆阻深度信念神经网络.png)
NATURE ELECTRONICS
NATURE ELECTRONICSIF40.9
PREAI
分享收藏Efficient and self-adaptive in-situ learning in multilayer memristor neural networks多层忆阻器神经网络的高效自适应原位学习NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏
查看更多内容