Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172752,
        author = {Abhishek Agwekar and Dr. Laxmi Singh},
        title = {Data-Driven Performance Evaluation of Analog Computing Circuits: Shape and Margin Analysis with Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {1273-1279},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172752},
        abstract = {This paper presents a novel approach to the design and analysis of shape-based analog computing (S-AC) circuits, leveraging machine learning tech-niques to enhance performance in VLSI technolo-gies. The study explores the key features of S-AC circuits, particularly their scalability, precision, speed, and power efficiency, as compared to con-ventional digital designs. Machine learning archi-tectures are integrated with mathematical function approximations to optimize the implementation of S-AC circuits, enabling efficient circuit simulations and performance evaluations. The input-output characteristics are mapped using a CMOS process, ensuring adaptability across different process var-iations. Notably, S-AC-based neural networks exhibit high resilience to temperature fluctuations, maintaining consistent accuracy. Furthermore, the study introduces a design margin and shape analy-sis framework, where the design parameter (S) and machine learning models play a crucial role in ensuring functional accuracy. Unlike traditional circuit design methods, the S-AC approach allows users to select prototype shapes based on specific application requirements, optimizing functional forms dynamically through machine learning. This research highlights the potential of machine learning-driven analog circuit design to advance scalable and efficient VLSI implementations, paving the way for next-generation computing architectures.},
        keywords = {Process Scalability, Margin Propagation, Machine Learning, S-AC Computing, VLSI, Machine Learning.},
        month = {February},
        }