5 HN users recommended this course5 months2016–2023score 6
Years with an HN recommendation, 2007–2026
Recommended repeatedly in 'where do I start with ML' threads as a clear, math-aware introduction.
The first lecture of Caltech's CS 156 Machine Learning course by Yaser Abu-Mostafa, introducing the learning problem and supervised, unsupervised and reinforcement learning. It is one of 18 lectures in the Learning from Data course.
“I have found the Caltech machine learning intro course to be the most elucidating of any resource so far” (HN, 2023)
I'm a neophyte to ML, but one course I very much enjoyed auditing was "Learning from Data" [1] taught by Caltech Professor Yaser Abu-Mostafa. I found concept of the _Learning Model_ particularly fresh representation of the ML activity (starting at 14:39 in the first video linked here [2]) [1]: [link] [2]: [this video]
Enjoyable course with a fresh presentation of the learning model
I have found the Caltech machine learning intro course to be the most elucidating of any resource so far: [this video] The delivery of the lecture material was like butter to me. Might work differently for others though.
Most elucidating ML intro resource, delivered clearly
there are some lectures about machine learning on youtube. I think they are good to watch: [this video] and [link] and my favorite channels are Standford and MIT open courseware [link] and [link]
Pattern Recognition and Machine Learning by Christopher Bishop. Book: [link] Notes: Its very very math heavy but if you really want to grasp the concepts and the idea around each topic, this is one of the way to go. Online Lectures: [this video] I like how he explains stuff and adds some context behind the math of each topic. Alternative: [link] A pretty good youtube channel that follows up on modern machine learning and he has all of his video tutorial demos on GitHub. Hope this helps fellow Machine Learner :)
Online lectures explaining the math and context behind each topic
Caltech machine learning intro course: [this video] karpathy's Zero to Hero series ( [link] ) meta llama 2 - is open source [link] Tools: ai - hosting Banana - Machine Learning Model Deployment on Serverless GPUs [link] pinecone - vector database: [link] how to run AI language models on a single cpu pc - [link]
[link] [this video] (incidentally for graycat, Yaser Abumostafa is a Muslim Egyptian immigrant from Cairo) He covers the VC dimension in [link] , and leaves the proof to an appendix of the book.
Caltech Learning from Data course covering VC dimension
Video list and Hacker News comment labels from HackerTube (prompted by @karpathy), released under ODC-By 1.0, built on the open-index/hacker-news archive. Hacker News data is provided by Y Combinator; comments remain the work of their authors. Video titles, channel names and thumbnails belong to their creators and are shown via YouTube. HackerTube Watch is an unofficial edition. Data export of 2026-10-31.
Plays via YouTube's privacy-enhanced embed
6 Hacker News comments
From the HN archive; up to 20 kept per video, favoring different commenters. Recommendations first.
Citations, criticism and jokes