Estimation of PSIJ in CMOS inverters via Knowledge Based Artificial Neural Networks

In this paper, a knowledge based artificial neural network is developed for predicting jitter for a CMOS inverter in the presence of power supply noise (PSN). The proposed ANN provides for efficient training in an hybrid approach using input data extracted from both analytical closed-form expressions as well as a circuit simulator. The proposed ANN demonstrates a reasonably accurate prediction of PSIJ with results that closely match with that from directly using a circuit simulator (ADS) for a case study with 50nm CMOS technology.