Transfer Learning Assisted Fast Design Migration Over Technology Nodes: A Study on Transformer Matching Network

In this study, we introduce an innovative methodology that leverages knowledge transfer from a pre-trained synthesis neural network (NN) model in one technology node and achieves swift and reliable design adaptation across different IC technologies, operating frequencies, and metal options. We prove this concept through simulation-based demonstrations focusing on the training and comparison of the coefficient of determination (R2) of NNs for 1:1 on-chip transformers in GlobalFoundries(GF) 22nm FDX (target domain), with/without transfer learning from a model trained in GF 45nm SOI (source domain). A striking observation is that a model trained with just 5% of target data, augmented by transfer learning, achieved better R2 than a model trained with 20% of data without transfer, which echoes the advantage seen from 1% to 5% data density. This demonstrates a notable reduction of 4 in the necessary dataset size highlighting the promise of utilizing transfer learning to mm-wave passive network design.