|
via Udemy |
Go to Course: https://www.udemy.com/course/vsd-machine-intelligence-in-eda-cad/
Certainly! Here's a detailed review and recommendation for the Coursera course based on the provided information: --- **Course Review and Recommendation: Machine Learning for Electronic Design Automation on Coursera** **Overview:** This engaging course was conducted during a webinar held on March 31, 2018, by Rohit Sharma, CEO of Paripath Inc., a seasoned expert with over 20 years of experience in electronic design automation (EDA). The course offers an in-depth exploration of how machine learning (ML) intersects with electronic design, specifically focusing on applications within CAD, EDA, and VLSI flows. **Content and Structure:** The course begins with foundational concepts, clarifying the relationship between electronic design automation and machine learning. It provides a comprehensive introduction to the main categories of ML—supervised and unsupervised learning—and discusses the frameworks available today, including general-purpose tools, big data processing platforms, and deep learning architectures, emphasizing their suitability for design automation tasks. A significant portion of the course focuses on applied theory, covering essential data manipulation techniques such as data sets, augmentation, normalization, and exploration. Rohit explains terminology and process flow, guiding learners on how to develop effective algorithms for product enhancement using machine learning. Practical examples, such as resistance estimation using datasets from 20nm technology and capacitance estimation via polynomial regression, make the concepts tangible. Further, the course introduces students to creating linear classifiers using logistic regression and discusses techniques like dimensionality reduction for managing large datasets efficiently—learning essential skills for scaling ML solutions. **Strengths:** - **Expert Instruction:** Rohit Sharma’s extensive experience and clear communication style make complex topics accessible. - **Real-World Applications:** The course emphasizes practical applications related to design automation, making it highly relevant for industry professionals. - **Comprehensive Coverage:** From fundamental ML concepts to specific use cases in EDA and VLSI, the content caters to learners seeking both breadth and depth. - **Focus on Data Handling:** The course highlights critical data analysis techniques, essential for successful ML implementation in design workflows. **Areas for Improvement:** - The course discusses mathematical concepts behind ML techniques, but more beginner-friendly explanations or additional resources could benefit those new to the field. - As it was originally a webinar, some sections may require supplementary reading or hands-on exercises for thorough understanding. **Recommendation:** This course is highly recommended for engineers, researchers, and students involved in electronic design, CAD, and VLSI who want to leverage machine learning to enhance their workflows. It’s particularly useful for those interested in understanding how to incorporate ML algorithms into design automation processes and make data-driven decisions. **Final Thoughts:** If you have a background in electronic design and wish to explore the integration of machine learning into your work, this course provides a solid foundation. Rohit Sharma’s insights and the course’s practical focus make it a valuable resource for advancing your knowledge in this rapidly evolving intersection of disciplines. --- Would you like me to customize this further or include specific details for a particular audience?
This webinar was conducted on 31st March 2018 with Rohit, CEO Paripath Inc.We start with Electronic design automation and what is machine learning. Then we will give overall introduction to categories of machine learning (supervised and unsupervised learning) and go about discussing that a little bit. Then we talk about the frameworks which are available today, like general purpose, big data processing and deep-learning, and which one is suitable for design automation. This is Machine Learning in general with a focus on CAD, EDA and VLSI flows. Then we talk about Applied Theory (data sets, data analysis like data augmentation, exploratory data analysis, normalization, randomization), as to what are the terms and terminologies and what do we do with that, accuracy, how do we develop the algorithm, essentially the things that are required to develop the solution flow, lets say, you as the company wants to add a feature in your product using machine learning, what you would be doing, and what your flow will look like and this is what is shown as pre-cursor of flight theory as what you should be looking out. And then we start with regression, which is first in supervised learning. In the regression, we will give couple of example, like first is resistance estimation, second is polynomial regression which is capacitance estimation. For resistance estimation, we have the dataset from 20nm technology. And finally, we go on to create a linear classifier using logistic regression. Next will be dimensionality reduction, meaning, you have a large dataset and how to you reduce the size of that so that you can run on a laptop or even on your cell phone. Then there is a big example of that. Everything has mathematics behind that, this wont be a part of the webinar.About Rohit - Rohit Sharma is Founder and CEO of Paripath Inc based in Milpitas, CA. He graduated from IIT Delhi.He has authored 2 books and published several papers in international conferences and journals. He has contributed to electronic design automation domain for over 20 years learning, improvising and designing solutions. He is passionate about many technical topics including Machine Learning, Analysis, Characterization and Modeling, which led him to architect guna - an advanced characterization software for modern nodes.He currently works for Paripath Inc.