Transfer Learning for Reuse of Analog Circuit Sizing Models Across Technology Nodes

计算机科学 节点(物理) 学习迁移 尺寸 试验数据 人工神经网络 试验装置 人工智能 数据点 机器学习 工程类 结构工程 艺术 视觉艺术 程序设计语言
作者
Zhengfeng Wu,Ioannis Savidis
标识
DOI:10.1109/iscas48785.2022.9937457
摘要

A transfer learning technique is proposed that utilizes models trained on data in one technology node to predict the performance of a circuit based on the sizing of transistors in another technology node. Specifically, neural networks optimally trained on data from the source technology node are adopted as pre-trained models. During transfer training, the front layers of the pre-trained models are frozen while the remaining layers are re-trained with significantly less data in the target technology node. The transfer learning technique is applied to the prediction of seven performance metrics of an operational amplifier based on seven design variables that include the sizing of transistors and capacitors. Models trained on a dataset containing 1602 simulated design points from a 180 nm process are transferred to predict the performance metrics of the op-amp utilizing only 100 simulated design points from a 65 nm process. During the training of the transferred models, the learning curve exhibits an improved starting point and a lower asymptotic error. Utilizing the same training set of 100 points from the 65 nm process, applying transfer learning reduces the normalized mean average error (MAE) on the test (inference) set in all cases by up to 50% as compared to training standalone models. For the transferred models, a detailed characterization of the test error as a function of the number of frozen layers is performed. Results indicate that the transferred gain predictor trained with only 100 data points provides a lower test error than the standalone model trained with 1000 data points without transfer learning in a 65 nm process. Therefore, transfer learning improves the sample efficiency of the training of the neural networks used for the prediction of the performance parameters of a circuit, which provides benefit for design migration when the collection of new circuit data is computationally costly in the target process node.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
有魅力老太完成签到 ,获得积分10
1秒前
山城的酒完成签到,获得积分10
1秒前
赵丽莹完成签到,获得积分10
1秒前
儒雅曼岚完成签到,获得积分10
1秒前
虚幻曼冬完成签到,获得积分10
2秒前
爱情小坦克完成签到,获得积分10
2秒前
rick的应助被Pann采纳,获得10
3秒前
guoxingliu完成签到,获得积分10
4秒前
大意的飞瑶完成签到,获得积分10
4秒前
single完成签到,获得积分10
5秒前
矮小的柠檬完成签到,获得积分10
5秒前
song完成签到,获得积分10
5秒前
CarryLJR发布了新的文献求助10
6秒前
haoran_man发布了新的文献求助10
7秒前
jiuzhijiu完成签到,获得积分10
8秒前
8秒前
思源的应助被horizon采纳,获得10
8秒前
毛毛余完成签到 ,获得积分10
9秒前
碳酸氢钠完成签到,获得积分0
9秒前
shower_009完成签到,获得积分10
9秒前
开朗大雁完成签到 ,获得积分10
9秒前
tyj完成签到,获得积分10
9秒前
暴躁的语风完成签到,获得积分10
9秒前
打打的应助被晚安采纳,获得10
9秒前
爆米花的应助被逍遥子采纳,获得10
10秒前
尘映ovo完成签到 ,获得积分10
10秒前
科研小能手完成签到,获得积分0
10秒前
12秒前
04d的应助被annie采纳,获得10
12秒前
喵喵大王完成签到 ,获得积分10
12秒前
wendy_1006完成签到 ,获得积分10
13秒前
14秒前
守护最好的坤坤完成签到,获得积分10
14秒前
hhh完成签到,获得积分10
15秒前
15秒前
16秒前
济民财完成签到,获得积分10
16秒前
彭于彦祖完成签到,获得积分0
16秒前
16秒前
梦露完成签到 ,获得积分10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8159174
求助须知:如何正确求助?哪些是违规求助? 9554642
关于积分的说明 21720253
捐赠科研通 7748830
什么是DOI,文献DOI怎么找? 3427184
关于科研通互助平台的介绍 2552091
邀请新用户注册赠送积分活动 2471464