These course reviews were inspired by Daniel Seita's Blog. When I was an undergraduate at UC Berkeley I often found myself reading through his course reviews (ie. CS 280, CS 288, etc) when deciding which grad courses to take. I also really like the layout of his blog a lot and I am using his source code as a template, so huge thanks Daniel!

These are the upper division machine learning courses (or at least courses I feel are related to machine learning education) I have taken while at UC Berkeley, listed in chronological order. I have listed course number, title, semester I took it, and grade I recieved. If you are interested in understanding the heirarchy (the natural order to take these courses) hkn has put together a nice explanation that I used quite a lot during my undergrad. A hyperlink will be embedded to each item as I get around to writing each of the reviews.

  • Math 110, Linear Algebra, Sophomore Fall 2019, A-
  • EECS 126, Probability and Random Processes, Sophomore Spring 2020, P
  • EECS 127, Optimization Models in Engineering, Sophomore Spring 2020, A-
  • CS 100, Principles & Techniques of Data Science, Sophomore Summer 2020, A
  • CS 188, Introduction to Artificial Intelligence, Sophomore Summer 2020, A-
  • CS 189, Introduction to Machine Learning, Junior Fall 2020, A
  • CS 182, Designing, Visualizing and Understanding Deep Neural Networks, Junior Spring 2021, A-
  • EE 120, Signals and Systems, Junior Spring 2021, P
  • CS 194-80, Full Stack Deep Learning, Junior Spring 2021, A
  • CS 194-26, Intro to Computer Vision and Computational Photography, Senior Fall 2021, A
  • CS 285, Deep Reinforcement Learning, Decision Making, and Control, Senior Fall 2021, A
  • CS 280, Computer Vision, Senior Spring 2022, A
  • CS 288, Natural Language Processing, Senior Spring 2022, A
  • CS H196A, Senior Honors Thesis Research, Senior Spring 2022, A+

My Overall Thoughts on Education at Berkeley

I think it would be helpful for readers to understand the perspective in which I write these course reviews so they can make their best judgment and decision. I have written some semblance of a preface or disclaimer to help readers understand my own biases.

I am a huge advocate for the Berkeley's course experience, especially when it comes to machine learning. However, Berkeley's educational experience is not limited to the courses it offers. There are plenty of ways to engage in education at UC Berkeley outside of just courses—research, clubs, internships, just to name a few. Just because I am a huge proponent for these courses, does not necessarily mean that you will also enjoy them and learn from them to the same extent that I did.

[still working on this section, more thoughts will be added soon...]