Domain knowledge-infused deep learning for automated analog/radio-frequency circuit parameter optimization
Domain knowledge-infused deep learning for automated analog/radio-frequency circuit parameter optimization
复制标题
DOI：
10.1145/3489517.3530501
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Weidong Cao;M. Benosman;Xuan Zhang;Rui Ma
中科院分区：
文献类型：
--
作者：
Weidong Cao;M. Benosman;Xuan Zhang;Rui Ma
模拟电路的设计自动化是一个长期的挑战。本文提出了一种通过图学习增强的强化学习方法，用于在预布局阶段自动化模拟电路参数优化，即，找到器件参数以满足期望的电路规格。与所有现有方法不同，我们的方法受到依赖于模拟电路设计领域知识的人类专家的启发（例如，电路拓扑和电路规范之间的耦合）来解决问题。通过最初将这些关键领域知识结合到多模态网络的策略训练中，该方法可以最好地学习电路参数和设计目标之间的复杂关系，从而在优化过程中实现最佳决策。在典型电路上的实验结果表明，该方法达到了人类水平的设计精度（~99%），效率是现有最佳方法的1.5倍。我们的方法也表现出更好的泛化能力，看不见的规格和电路性能优化的最优性。此外，它适用于在新兴半导体技术上设计射频电路，打破了现有学习方法在设计传统模拟电路时的局限性。
The design automation of analog circuits is a longstanding challenge. This paper presents a reinforcement learning method enhanced by graph learning to automate the analog circuit parameter optimization at the pre-layout stage, i.e., finding device parameters to fulfill desired circuit specifications. Unlike all prior methods, our approach is inspired by human experts who rely on domain knowledge of analog circuit design (e.g., circuit topology and couplings between circuit specifications) to tackle the problem. By originally incorporating such key domain knowledge into policy training with a multimodal network, the method best learns the complex relations between circuit parameters and design targets, enabling optimal decisions in the optimization process. Experimental results on exemplary circuits show it achieves human-level design accuracy (~99%) with 1.5× efficiency of existing best-performing methods. Our method also shows better generalization ability to unseen specifications and optimality in circuit performance optimization. Moreover, it applies to design radio-frequency circuits on emerging semiconductor technologies, breaking the limitations of prior learning methods in designing conventional analog circuits.