Efficient Layout Hotspot Detection via Binarized Residual Neural Network

机译：通过二值化残差神经网络的高效布局热点检测

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Layout hotspot detection is of great importance in the physical verification flow. Deep neural network models have been applied to hotspot detection and achieved great successes. The layouts can be viewed as binary images. The binarized neural network can thus be suitable for the hotspot detection problem. In this paper we propose a new deep learning architecture based on binarized neural networks (BNNs) to speed up the neural networks in hotspot detection. A new binarized residual neural network is carefully designed for hotspot detection. Experimental results on ICCAD 2012 Contest benchmarks show that our architecture outperforms all previous hotspot detectors in detecting accuracy and has an 8x speedup over the best deep learning-based solution.

机译：布局热点检测在物理验证流程中非常重要。深度神经网络模型已应用于热点检测，并取得了巨大的成功。布局可以视为二进制图像。因此，二值化神经网络可以适用于热点检测问题。在本文中，我们提出了一种基于二值神经网络（BNN）的新型深度学习架构，以加快热点检测中的神经网络速度。精心设计了一种新的二值化残差神经网络用于热点检测。在ICCAD 2012竞赛基准测试中的实验结果表明，我们的体系结构在检测精度方面优于所有以前的热点检测器，并且比基于深度学习的最佳解决方案高出8倍。

著录项

来源
《2019 56th ACM/IEEE Design Automation Conference》|2019年|1-6|共6页
会议地点 Las Vegas(US)
作者
Yiyang Jiang; Fan Yang; Hengliang Zhu; Bei Yu; Dian Zhou; Xuan Zeng;
展开▼
作者单位

State Key Lab of ASIC System, Fudan University, China;

State Key Lab of ASIC System, Fudan University, China;

State Key Lab of ASIC System, Fudan University, China;

Chinese University of Hong Kong, Hong Kong, China;

University of Texas at Dallas, USA;

State Key Lab of ASIC System, Fudan University, China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Neural networks; Convolution; Layout; Detectors; Kernel; Computer architecture;

机译：神经网络;卷积;布局;检测器;内核;计算机体系结构;;

相似文献

外文文献
中文文献
专利

1. Efficient Object Detection Using Embedded Binarized Neural Networks [J] . Jaeha Kung, David Zhang, Gooitzen van der Wal, Journal of VLSI signal processing systems for signal, image, and video technology . 2018,第6期

机译：使用嵌入式二值神经网络的有效目标检测
2. An efficient unconstrained facial expression recognition algorithm based on Stack Binarized Auto-encoders and Binarized Neural Networks [J] . Sun Wenyun, Zhao Haitao, Jin Zhong Neurocomputing . 2017,第deca6期

机译：基于堆栈二值化自动编码器和二值化神经网络的高效无约束表情识别算法
3. AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution [J] . HyunJin Kim PeerJ Computer Science . 2021,第a期

机译：ARESB-NET：使用快捷级联和随机分组卷积的准确剩余二值化神经网络
4. Efficient Layout Hotspot Detection via Binarized Residual Neural Network [C] . Yiyang Jiang, Fan Yang, Hengliang Zhu, ACM/IEEE Design Automation Conference . 2019

机译：通过二金属化残差神经网络测量的高效布局热点检测
5. Efficient low-degree interconnection networks for parallel processing: Topologies, algorithms, VLSI layouts, and fault tolerance. [D] . Yeh, Chi-Hsiang. 1998

机译：用于并行处理的高效低度互连网络：拓扑，算法，VLSI布局和容错能力。
6. Toward Scalable Efficient and Accurate Deep Spiking Neural Networks With Backward Residual Connections Stochastic Softmax and Hybridization [O] . Priyadarshini Panda, Sai Aparna Aketi, Kaushik Roy 2020

机译：朝着可扩展高效准确的深度尖峰神经网络具有向后剩余连接随机软墨乳和杂交
7. Peer Review #2 of "AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution (v0.1)" [O] . 2021

机译：同行评论“Aresb-net：使用快捷级联和随机分组的卷积（v0.1）”的准确残余二金属化神经网络中的＃2

Efficient Layout Hotspot Detection via Binarized Residual Neural Network

摘要

著录项

相似文献

相关主题

期刊订阅