A three-course Coursera specialization from the University of Washington, taught by Carlos Guestrin and Emily Fox, covering core machine learning methods such as regression, classification, and neural networks, with Python-based assignments. It explains the underlying math without going deep into theory.

Commenters call it well organized with good lectures, and say it explains the math behind the algorithms in a rigorous but approachable way.

What commenters said (8)

1. Strongly recommendstgokh2016in “Ask HN: What is your goto resource for learning about big data, ML, AI etc?”

   I'm a huge fan of the rest of this Coursera specialization (or was, until they started charging to submit assignments for it mid-specialization, but I digress...)

   Carlos and Emily do a great job diving deeper than most other online courses into the math behind different algorithms without making the math too theoretical. I'm a grad student in engineering, so I wanted to understand not only how to run these algorithms but also how they work and these courses were great for learning in a mathematically rigorous but still approachable sort of way.

   The only criticism I've heard of this series is that it uses Turi/Dato/Graphlab instead of SciKit-Learn. I did the courses that exist so far using GraphLab, but I'm starting to redo the assignments using SciKit now so that I learn that toolkit as well.

2. Recommendslemonghost2016in “Machine Learning for Software Engineers”

   I've completed three of the courses in the ML specialization on coursera (The UW one) and I'd definitely recommend it. It uses python (which I prefer over R or matlab) and it's really well organized with good lectures.

3. Recommendssndean2016in “Ask HN: Master vs. Udacity nanodegree”

   As a third, shorter (and cheaper) option I'd suggest the new Coursera ML course [0]. If you're short on money, they'll let you take the courses for free.

   I don't know how expensive Master's degrees are in Barcelona, but GA Tech has a online Master's in CS for ~$500 per course [1], where you could focus on ML.

   [0] https://www.coursera.org/specializations/machine-learning [1] https://www.omscs.gatech.edu/

4. Mentionsjonnycoder2025in “Ask HN: How to learn AI from first principles?”

   I've taken part 1 of 3 in Andrew Ng's machine learning specialization which covers the math for supervised learning, linear regression, etc. As I started part 2 (neural networks), it built off the math from part 1 such as the sigmoid activation function. This is what I think of when the OP refers to learning ML from first principles. I highly recommend Andrew Ng's course and I feel like I need to take it again to really understand those basic building blocks.

5. MentionsSlix2023in “Dive into Deep Learning: Interactive deep learning book with codes and maths”

   I'm running through Andrew Ng's "Machine Learning Specialization" course on Coursera right now. I plan to do his "Deep Learning Specialization" immediately after.

   There's not a lot of formulas and math so far, which concerns me because I eventually want to understand papers.

6. Mentionsundoware2022in “Ask HN: How bad is hiring going to be within the next year?”

   My advice is to get 'ML' on your resume, some way, somehow, along with some selection of: TypeScript, React, Python, C#, Java, Linux, and Kubernetes.

   Start with a good online free course like https://www.coursera.org/specializations/machine-learning-in...

   You don't have to be a full-bore data scientist to benefit from the surging interest in ML -- for example, I've made my current focus 'UX for data scientists', I focus on trying to make interfaces that are pleasing to people working in ML, and this, I am pleased to say, just got my ass hired.

   It's also salient to know that, over the next decade, while tech salaries will likely trend down (esp. as CoPilot, nocode/lowcode, etc continue to make our lives easier and hence less lucrative ;D) the *amount of addressable work* in ML specifically will almost certainly offset this change.

   YMMV in other tech specializations, but I'd still rather be in our industry than most others. Again, there's plenty of work in MLOps that does not require being a data scientist.

   Finally, if you can physically live in a geolocation with lower cost of living (or better yet, a currency that is weaker than USD) you can be the lower-cost option that everyone ditches Fancy McSanFransiscoPants for in 2023. Be sure to blog and show your work on GH ;D

7. Mentionslovelearning2022in “Ask HN: Courses/resources you can recommend to start with ML/AI”

   Because you're looking for fundamentals and concepts rather than coding, I suggest Andrew Ng's courses [1], especially [2]. His teaching is beginner-friendly.

   [1]: https://www.coursera.org/courses?query=machine%20learning%20...

   [2]: https://www.coursera.org/specializations/machine-learning-in...

8. Mentionsmailarchis2018in “Ask HN: How old are you (optional) and what was the last thing that you learned?”

   34. Learning Economics. Reading Principles of Economics by N. Gregory Mankiw . I didn't take a course in Economics while in college and am trying to make up for it and build a better understanding of how the world operates.

   I finished the Machine Learning specialization offered by UWash on Coursera a few months back, but I am not happy with my grasp on the subject and plan to dive deeper with a project and few books in next few months.

Related courses

• Deep Learning Specialization (Andrew Ng)Coursera · 31 recommenders
• Machine Learning (Andrew Ng)Coursera · 240 recommenders
• Practical Deep Learning for Codersfast.ai · 112 recommenders
• CS231n: Convolutional Neural Networks for Visual RecognitionStanford University · 39 recommenders
• Neural Networks for Machine Learning (Geoffrey Hinton)Coursera · 25 recommenders
• CS229 Machine LearningStanford University · 20 recommenders
• Learning From DataCaltech · 20 recommenders
• CS188 Introduction to Artificial IntelligenceUC Berkeley · 18 recommenders