This book delivers a focused, technical exploration of automated analog and RF integrated circuit sizing under process, voltage, and temperature variations, guiding readers through foundational concepts, current methodologies, and advanced machinelearningdriven approaches. It first examines multiple reinforcementlearningbased strategies for embedding PVT conditions directly into modern sizing flows, clarifying their conceptual differences and practical implications. It then explores a complementary deeplearningassisted approach that leverages ANNbased performance regressors, transfer learning, and adaptive refinement to accelerate simulationdriven optimization without requiring extensive cornerspecific datasets. Together, these chapters provide a grounded overview of current techniques and ongoing developments in automated analog IC design.

Compares different approaches for the inclusion of PVT corners into reinforcement learning agents Covers implementation of reinforcement learning for the design of analog and radio-frequency integrated circuits Focuses on automating the design of analog and radio-frequency integrated circuits

Autorentext

Pedro Paiva received a B.Sc. degree in Electrical and Computer Engineering from the Instituto Superior Técnico (IST), University of Lisbon, Portugal, in 2023. He is currently completing his M.Sc. degree in the field of control, robotics, and artificial intelligence at the same institution, with his thesis focusing on electronic design automation of analog integrated circuits. His research interests include machine learning and deep learning. José Costa received a B.Sc. degree in Electrical and Computer Engineering from the Instituto Superior Técnico (IST), University of Lisbon, Portugal, in 2025. His research interests include machine learning and deep learning. Filipe Azevedo received his M.Sc. degree in Computer Science and Engineering from the Instituto Superior Técnico (IST), University of Lisbon, Portugal, in 2020. He is currently working on his Ph.D. degree in Electrical and Computer Engineering from the same university, while working with Instituto de Telecomunicações. His research interests include machine learning and generative AI applied to analog IC design automation. Ricardo Martins received the Ph.D. degree in Electrical and Computer Engineering from Instituto Superior Técnico—University of Lisbon (IST-UL), Portugal, in 2015. He is with Instituto de Telecomunicações since 2011 developing electronic design automation tools and in 2022 became Assistant Professor of the electronics scientific area of the Department of Electrical and Computer Engineering of IST-UL.

Inhalt

Chapter 1 Introduction.- Chapter 2 State-of-the-Art.- Chapter 3 PVT Corner Conditions within Reinforcement Learning-based Analog IC Sizing.- Chapter 4 PVT Corner Analog IC Sizing Optimizations Boosted by ANN[1]based Performance Regressors and Transfer Learning.