How to Learn?
The best way to learn something like machine learning is to begin with a small project and learn things on the way. This was how my journey started as well. My introduction to Machine Learning began with my masters project which involved a small classification problem on astronomical timeseries data (photometric light curves of variable stars) where I used traditional ML algorithms like SVM etc.
While on the project and when in doubt, I often return to a few of my trusted books to solve them before going to other resources that are available elsewhere on the internet etc. Video lectures are also very helpful but there aren't a lot of them available. One of the most popular ones is by Andrew N. G. on coursera.
When you advance in a particular topic, start reading research papers on the topic and go through blogs that might also additionally provide code. This is required since things like the design of deep learning networks and other technical details are often found there rather than in books. Once you understand things, use tools like Chat-GPT to your advantage.
Teaching others helps, but if you do not have such an opportunity maybe writing small articles and publishing them on a blog would be very helpful. I write articles that I publish on a personal blog (not maintained currently). I talk about some of the tools and resource requirements in an article I have published in my blog
List of Resources
Here is a list of resources that I have used (atleast partially). I also have a list of topics in machine learning where I link to specific resources- Video
- Andrew N.G.'s course on Cousera (Deeplearning.ai)
- 3Blue1Brown has a playlist on neural netowrks.
- Books
- Bishop, C. M. 2006, Pattern recognition and machine learning (New York: Springer)
- Chollet, F. 2025, Deep Learning with Python, Third Edition(S.l.: Manning Publications)
- Goodfellow, I., Bengio, Y., & Courville, A. 2016, Deep learning (Cambridge, Mass: The MIT press)
- Bishop, C. M., & Bishop, H. 2024, Deep Learning: Foundations and Concepts (Cham: Springer International Publishing)
- Marsland, S. 2014, Machine Learning: An Algorithmic Perspective (2nd edn; Chapman and Hall/CRC)
- Ivezić, Ž., Connolly, A. J., VanderPlas, J., Gray, A., & VanderPlas, J. 2020, Statistics, data mining, and machine learning in astronomy: a practical python guide for the analysis of survey data (Updated edition; Princeton Oxford: Princeton University Press)
- Deep Learning for Computer Vision by Adrian Rosebrock
- More books Some books that are generally deemed good and which I would like to read at some point.
- Information Theory, Inference and Learning Algorithms by David J. C. MacKay
- An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani & Jonathan Taylor
- Artificial Intelligence: A Modern Approach by Stuart Russell & Peter Norvig