.png){kind=icon}
返回
Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-023-40770-4.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Analog in-memory computing-a promising approach for energy-efficient acceleration of deep learning workloads-computes matrix-vector multiplications but only approximately, due to nonidealities that often are non-deterministic or nonlinear. This can adversely impact the achievable inference accuracy. Here, we develop an hardware-aware retraining approach to systematically examine the accuracy of analog in-memory computing across multiple network topologies, and investigate sensitivity and robustness to a broad set of nonidealities. By introducing a realistic crossbar model, we improve significantly on earlier retraining approaches. We show that many larger-scale deep neural networks-including convnets, recurrent networks, and transformers-can in fact be successfully retrained to show iso-accuracy with the floating point implementation. Our results further suggest that nonidealities that add noise to the inputs or outputs, not the weights, have the largest impact on accuracy, and that recurrent networks are particularly robust to all nonidealities.
Keyword:
NEURAL-NETWORKS
RESISTANCE
DEVICE
ARRAY
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:
15.7
论文数:
9.4W
被引数:
91.2W
机构
引用论文
.png){kind=icon}
A Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points一种基于心电图基准点的分层心律分类方法OAAI
OAAI分享收藏分享收藏Tolerating Noise Effects in Processing-in-Memory Systems for Neural Networks: A Hardware-Software Codesign Perspective在神经网络的内存处理系统中容忍噪声影响: 硬件-软件协同设计的观点OAAI
OAAI分享收藏
查看更多内容