arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1812.02734cs.LG
收藏

学习设计电路

Learning to Design Circuits

Massachusetts Institute of Technology(麻省理工学院)

Hanrui Wang, Jiacheng Yang, Hae-Seung Lee, Song Han

摘要:

模拟IC设计依赖于人类专家凭借经验和直觉来搜索满足电路规格的参数,这是高度劳动密集型的,耗时的并且是次优的。机器学习是一个很有前途的工具,可以自动化这个过程。然而,由于训练数据的低可用性,监督学习很难完成这项任务:1)电路仿真速度慢,因此生成大规模数据集很耗时; 2)大多数电路设计都是单个IC公司内部的和解IP,这使得收集大规模数据集的成本很高。我们提出了学习设计电路(L2 DC),以利用强化学习,学习有效地生成新的电路数据和优化电路。我们修复了原理图,并通过训练一个没有关于优化电路的先验知识的RL代理来自动优化晶体管的参数。在迭代获得观察结果、生成一组新的晶体管参数、获得奖励并调整模型之后,L2 DC能够优化电路。我们评估两个跨谐放大器上的L2 DC。经过一天的训练,我们的RL代理可以实现与经过四分之一训练的人类专家相当或更好的性能。它首先学会满足硬约束(例如,增益、带宽),然后学习优化好的目标(例如,功率)。与网格搜索辅助的人工设计相比,L2 DC可以在性能相当的情况下实现$\mathbf{250}\boldsymbol{\times}$更高的样本效率。在相同的运行时间约束下,L2 DC的性能也优于贝叶斯优化。

英文摘要:

Analog IC design relies on human experts to search for parameters that satisfy circuit specifications with their experience and intuitions, which is highly labor intensive, time consuming and suboptimal. Machine learning is a promising tool to automate this process. However, supervised learning is difficult for this task due to the low availability of training data: 1) Circuit simulation is slow, thus generating large-scale dataset is time-consuming; 2) Most circuit designs are propitiatory IPs within individual IC companies, making it expensive to collect large-scale datasets. We propose Learning to Design Circuits (L2DC) to leverage reinforcement learning that learns to efficiently generate new circuits data and to optimize circuits. We fix the schematic, and optimize the parameters of the transistors automatically by training an RL agent with no prior knowledge about optimizing circuits. After iteratively getting observations, generating a new set of transistor parameters, getting a reward, and adjusting the model, L2DC is able to optimize circuits. We evaluate L2DC on two transimpedance amplifiers. Trained for a day, our RL agent can achieve comparable or better performance than human experts trained for a quarter. It first learns to meet hard-constraints (eg. gain, bandwidth), and then learns to optimize good-to-have targets (eg. area, power). Compared with grid search-aided human design, L2DC can achieve $\mathbf{250}\boldsymbol{\times}$ higher sample efficiency with comparable performance. Under the same runtime constraint, the performance of L2DC is also better than Bayesian Optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑