International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Topology Selection Method for CMOS Analog Circuits Using Machine Learning

Author : Stutee Pradhan ¹ Shashank M Rao ² Harshitha N ³ Muralidhar Shanbhag ⁴

Date of Publication :1st August 2022

Abstract: Topology selection is an important part of analog circuit design and choosing the right topology manually is timeconsuming. We present a new technique of topology selection for CMOS analog circuits. The technique involves predicting different amplifier topologies using a Machine Learning (ML) algorithm. The proposed implementation helps reduce errors and time spent on tedious, repetitive circuit designing tasks. It is aimed at reducing resource requirements and enhancing speed. For demonstration, we have focused on predicting 3 different amplifier topologies namely common drain, cascode amplifier and two stage OPAMP. 9 different performance parameters are used to distinguish different topologies. The topology prediction is performed using 5 Machine Learning algorithms and the performances of the algorithms are compared to find the best algorithm for topology selection.

Reference :

1. A. Gerlach, T. Rosahl, F. T. Eitrich, and J. Scheible, “A generic topology selection method for analog circuits with embedded circuit sizing demonstrated on the OTA example,” in Conf. for Design and Test in Europe, 2017, pp. 898–901.
2. B. Razavi, “Design of Analog CMOS Intergrated Circuits.”
3. P. Bhattacharjee, A. J. Mondal, and A. Majumder, “A constraint driven technique for MOS amplifier design,” 2016.
4. A. Sadeqi, J. Rahmani, S. Habibifar, M. A. Khan, and H. M. Munir, “Design method for two-Stage CMOS operational amplifier applying load/miller capacitor compensation,” Computational Research Progress in Applied Science & Engineering, vol. 06, no. 03, pp. 153–162, 2020.
5. J. Peng, K. L. Lee, and G. M. Ingersoll, “An Introduction to Logistic Regression Analysis and Reporting,” Journal of Educational Research- J EDUC RES, vol. 96, 2002
6. K. Taunk, S. De, S. Verma, and A. Swetapadma, “A Brief Review of Nearest Neighbor Algorithm for Learning and Classification,” 2019 International Conference on Intelligent Computing and Control Systems (ICCS), pp. 1255–1260, 2019.
7. Y. Zhang, L. C., W. L., and Y. A., “Support Vector Machine Classification Algorithm and Its Application,” in Information Computing and Applications. ICICA 2012, vol. 308. Springer, 2012.
8. V. N. Vapnik, “The Nature of Statistical Learning Theory,” 2000.
9. A. Gershman, A. Meisels, K. Lüke, L. Rokach, A. Schclar, and A. Sturm, “A Decision Tree Based Recommender System,” 2010.
10. S. D. Jadhav and H. Channe, “Efficient Recommendation System Using Decision Tree Classifier and Collaborative Filtering,” 2016.
11. L. Breiman, “Random Forests,” Machine Learning, vol. 45, 2001.
12. R. Caruana and A. Niculescu-Mizil, “An empirical comparison of supervised learning algorithms,” in 23rd International Conference on Machine Learning. ACM Press, 2006.