Knowledge-Based Bidirectional Recurrent Neural Network Approach for Efficient Prediction of Jitter in a Chain of CMOS Inverters

• Published in: IEEE journal on multiscale and multiphysics computational techniques pp. 1 - 14
• Main Authors: Javaid, Ahsan, Achar, Ramachandra, Tripathi, Jai N.
• Format: Journal Article
• Language: English
• Published: IEEE 2025
• Subjects: Artificial neural networks; bidirectional recurrent neural network (BiRANN); CMOS inverter chain; data noise; ground bounce; Integrated circuit modeling; Inverters; Jitter; Knowledge based systems; knowledge-based neural network (KBNN); Noise; Power supplies; power supply noise; Recurrent neural networks; Semiconductor device modeling; Transistors
• ISSN: 2379-8815; 2379-8815
• DOI: 10.1109/JMMCT.2025.3602632

An efficient hybrid approach based on combining the bidirectional recurrent neural network with knowledge-based neural network is presented to predict jitter in a chain of CMOS inverters in the presence of multiple noise sources. The new method achieves a reasonable accuracy and provides for efficient training using input data obtained from both a circuit simulator as well as analytical relations. The proposed approach can also estimate jitter for each inverter in the chain by only employing the accurate training data associated with the first inverter, resulting in a significant increase in speed compared to conventional approaches.