Machine-learning/AI-based Automated Layout Synthesis of Analog and Mixed-Signal Integrated Circuits

Analog and mixed-signal circuits are essential building blocks in many applications, while the design cost of these circuits is much higher than their digital counterparts because of their higher complexity and the lack of automation tools. The overall goal of this project is to increase the productivity, optimality and correctness of designing integrated analog electronic circuits. The novelty of the research is to explore and apply innovative algorithmic techniques, including AI and machine learning, to do this. The main point of this project lies in how to synthesize analog and mixed-signal circuits layout of comparable or higher quality without human involvement at minimum design cost.