With the rapid progress of artificial intelligence, data-driven methods are increasingly influencing all areas of electronic design automation (EDA). However, the analog and mixed-signal (AMS) domain still relies heavily on human expertise and manual design iterations, making automation a long-standing challenge. This seminar introduces a machine learning–based methodology for topology synthesis of analog and mixed-signal circuits. The proposed framework leverages AI techniques to automatically generate topologies that satisfy given performance specifications. By integrating learning-based models with design space exploration, the approach aims to significantly accelerate the early-stage design process while maintaining design quality. Experimental results demonstrate the potential of this methodology to advance automation in analog EDA.
14/11/2025 11:00 - 12:00
ESAT Aula L
