← blog
learning machine learning
2025/03/23
I became interested in machine learning during my third year, when I came across
Yann LeCunn's graduate ML course on youtube. From then on, I've bookmarked many sites
that were helpful for learning machine learning, and thought I would organize them here.
Many of them featured notebooks, which were also great for learning PyTorch and JAX.
-
Yann LeCunn's Deep Learning Course. (2020, 2021)
- Thanks to
Alfredo Canziani (course instructor) for making the resources open source
- I enjoyed the lectures, also available on youtube
-
University of Amsterdam DL Notebooks.
(link)
- Very detailed with many examples in both JAX and PyTorch
-
Kevin Murphy's Probabilistic Machine Learning.
(PML1,
PML2)
- Both thorough references for a detailed understanding of probabilistic ML as of 2024
- The book's structure follows the development of each method which I found interesting
-
Berkeley Deep Reinforcement Learning.
(link)
-
Vardan Papyan's Deep Learning: Theory and Data Science.
(link)
- A great introduction to theoretical results in deep learning
- I took this course in Fall 2023
-
Yang Song's Intro to Score-Based Modeling.
(link)
- Great for understanding score-based generative models
-
Geoffrey Hinton's Deep Learning course. (youtube)
- Neat that you can learn about RBMs from the man himself
-
3Blue1Brown Machine Learning Intro. (youtube)
-
lucidrains ViTs (repo)
- Great for understanding ViTs with minimal examples
I also took notes in my regression and time series courses which were generally helpful for understanding statistical modeling
-
Linear regression (pdf)
-
Time series (pdf)
If you feel that there's a great resource out there that is missing, email me!