Lecture 01 - The Learning Problem

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]: [VIDEO]

I have found the Caltech machine learning intro course to be the most elucidating of any resource so far: [VIDEO] The delivery of the lecture material was like butter to me. Might work differently for others though.

there are some lectures about machine learning on youtube. I think they are good to watch: [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: [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 :)

Caltech machine learning intro course: [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] [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.