About this document
Hybrid AI-Optimization Method For Latent Defect Detection Through Test Transistor Insertion by andyzhongwl is a document available to read on EtoBox.
This paper presents a hybrid AI-optimization method for detecting latent defects in analog circuits by inserting test transistors and utilizing a neural network classifier. The approach effectively identifies optimal insertion points for the transistors, achieving over 90% detection coverage for pinhole defects in 40nm CMOS opamp circuits. The methodology combines simulated annealing optimization with neural network feedback to maximize defect coverage while minimizing silicon area overhead.
- Author
- andyzhongwl
- Language
- EN