I have just completed the ML Specialization, what books would you recommend that would further build my foundations strong in ML. I want to get a very thorough understanding of this field.
Would also like to mention that I have a CS degree. Please help your brother out here
3 Likes
I think the MLS forum area has a thread that lists some additional resources.
2 Likes
Can you please drop a link to it @TMosh
Were you unable to find the MLS FAQ?
This thread has a link to the FAQ and Resources categories.
1 Like
Looked at courser’s mls faq, no I couldn’t find it
Not on Coursera, it’s here on the DeepLearning.AI site (see the link I posted in my previous reply).
Here’s a bibliography thread from DLS.
You can find that linked from the DLS FAQ Thread, which is also worth a look just in general.
1 Like
Probably check the web
Having recently completed a couple Stanford University SCPD graduate-level courses on machine learning, the most inclusive ML book is the two volume set “Probabilistic Machine Learning: An Introduction” by Kevin P Murphy in 2022. Second choice is “Deep Learning” by Goodfellow, Bengio & Courville.
Depending on how good your probability background is, you might need another book “A First Course in Probability” by Sheldon Ross, which is recommended by many courses at Stanford. Bayes’ Rule, random variables and expectation are so important to understanding ML algorithms.
5 Likes
“Introduction to Machine Learning with Python” by Andreas C. Müller and Sarah Guido.
Now I am just a newbie in this as you but this was the first ML book I read before ever going much into the theory and I found it very great. It offers a practical guide to implementing machine learning using Python and scikit-learn. It covers fundamental concepts, model evaluation, and real-world applications. It does not have much focus on deep learning but I believe its very good to get used to the ML environment as well as understanding dealing with data.
3 Likes
Machine Learning by Bishop and Deep Learning by Goodfellow