Course

Unit 1:

Introduction: Aims and applications of machine learning, Linear and Logistic Regression, Instance based learning, Bayesian learning, Support Vector Machine, Kernel function.

Unit 2 :

Learning Algorithms Scripting concepts, Shell responsibilities, OS, h/w, kernel, File system, passing arguments, Process, Networking, Version control processes

Unit 3 :

Taxonomy for Machine Learning in VLSI Design-Scope of machine learning in VLSI Physical Design. Machine Learning for Fabrication. Lithographic Process Models: Masks, and Physical Design, Yield Enhancements. Logic Synthesis and Physical Design, Verification and testing, Machine Learning-Based Aging Analysis

Course Objectives

• Understanding core Machine Learning concepts and algorithms
• Applying Machine Learning concepts to VLSI design challenges
• Developing practical skills using Machine Learning algorithms in VLSI design process

Course Outcomes: At the end of the course, the student should be able to

• CO1: Identify the goals, applications, types and design issues of machine learning techniques.
• CO2: Discover shell script programmatically using different features and debugging the code
• CO3: Describe machine learning in VLSI EDA for automation.

Skills Acquired: Use of Machine learning in VLSI Design and Automation

CO-PO Mapping:

• Ethem Alpaydın, Introduction to Machine Learning , MIT Press, 4^th  Edition, 2020.
• Guyue Huang, Jingbo Hu, et al., Machine Learning for Electronic Design Automation: A Survey. ACM Trans. Des. Autom. Electron. Syst. 26, 5, Article 40 (September 2021)
• Shell Programming in Unix, Linux and OS X: The Fourth Edition of Unix Shell Programming, Stephen G. Kochan, Patrick H. Wood, Addison-Wesley, 2016.
• “Machine Learning in VLSI Computer-Aided Design”, Ibrahim (Abe) M. Elfadel Duane S. Boning Xin Li,  Springer International Publishing, 2019.