Instructor

Prof. Amit Sethi

Semester

Spring 2023

Course Difficulty

1. If you have previous exposure to ML, it should be a rather easy course especially the assignments which ask you to code up models from scratch. Even though the course content is not tough but is quite vast and hence requires consistent efforts from one’s end if you expect to get a good grade. I would recommend you taking this course over CS419 in your 4th semester if you are more interested about the implementation and hence do not care to be a bit hand-wavy about the mathematical nitty-gritties.

Time commitment needed

Assuming you have no prior experience in the domain of ML, roughly 6 hours of self-study per week should do.

Grading Statistics

The professor follows absolute grading which he would announce in the very first lecture. 100+ would yield AP, 90+ would yield AA, 80+ would yield AB and so on…

He also gave significant bonus marks in the assignments, course project, mid-semester and the end-semester examinations. Hence, one can very easily score 90+ given he/she is regular and is putting consistent efforts. Here is the grading statistics for the time when I took this course :

AA 39 AB 37 AP 2 AU 38 BB 42 BC 39 CC 28 CD 31 DD 9 FR 9

Attendance Policy

The professor does not have any attendance policy but encourages you to attend classes and ask a lot of doubts. He also discussed the solutions of many questions that would straight-up appear in the paper in some way or the other. This was one of the major reasons why despite the no-attendance policy, people like me still attended his lectures.

Teaching Style

His classes were extremely engaging and perfectly adequate for conceptual understanding. He is very thorough in most aspects and hence we did not need to refer to any other course. He would also take up extra doubt sessions before the examinations to make sure that every student can score well in them. He also uploaded his prerecorded lectures on YT for those who could not make it to the lectures for whatsoever reason : https://www.youtube.com/watch?v=QhDlmPhFkNk&list=PLZKhx5nBXhfhL28m4mjIM5kSwh5gUV2k6

Feedback on Assignments/ Tutorials/ Projects

This part of the course represents a pivotal learning opportunity, focusing on the practical application of Machine Learning to real-world problems. The majority of projects within this phase have adopted Deep Learning techniques, which aligns with the prevailing trend in the field. Dedication and genuine commitment to your project can yield impressive results, both in terms of your understanding of the subject matter and your academic performance.

When it comes to assignments, they are structured in a way that allows for a comfortable and manageable workload, provided that you begin working on them with ample time in advance. This approach enables students to consistently achieve full marks.

Feedback on Exams (Written Evaluation)

The exams in this course strike a balance between being moderately challenging and intellectually stimulating. They do not demand rote memorization, which means you won’t need to cram facts and figures. Instead, the professor takes great care in crafting thought-provoking questions that encourage you to apply your understanding of the material.

Moreover, the inclusion of bonus marking opportunities makes it quite feasible to achieve decent scores. These bonus points provide an additional avenue for you to enhance your performance, further emphasizing the professor’s commitment to promoting a deep understanding of the subject matter.

In essence, the exams in this course are designed to foster critical thinking and problem-solving skills. By engaging with the material and considering the bonus marking opportunities, you can confidently aim for strong academic results while genuinely grasping the core concepts of the subject.

Future Tracks

I would say this is one of the most useful courses a student can do, in terms of opening avenues to newer job/internship/research profiles. The next logical continuation could be CS 726 : Advanced Machine Learning or EE782 : Advanced Machine Learning taken by the same professor.

Course Importance

This course is very important if you want a career in AI. I also believe basic ML awareness will be required in most technical roles in the upcoming years. Hence, I would strongly recommend everyone to take EE769 during their time at IITB.

Additional Details

Christopher Bishop - Pattern Recognition and Machine Learning

Shai Shalev - Understanding ML

Pattern Classification - Duda, Hart and Stork

Written By

Swapnoneel Kayal