There is an extensive bibliography on machine learning, both practical (the most of books) and (several) on theoretical foundations.
What is (in your opinion) the best book related to theoretical foundations that you have read?
You may take a look into "Probabilistic Machine Learning" - a book series by Kevin Murphy, https://probml.github.io/pml-book/. Covers a comprehensive overview.
Dear sir
Greeting and regards
2 years ago, I struggled to find the best machine-learning books that contain both theoretical(Algorithms) and analytical(codes) and I figured out a book name; Machine Learning with PyTorch and Scikit-Learn Develop machine learning and deep learning models with Python, written by Sebastian Raschka, Yuxi (Hayden) Liu,Vahid Mirjalili. the book covers all the readers with their knowledge level. It is the best-written book of many others I have read about. But please bear in mind if you want to be an expert in this field you need to study other books separately that have covered matplotlib, pandas library,numpy and so on. please for matplotlib study this book:Interactive Data Visualization with Python(Abha Belorkar, Sharath Chandra Guntuku, Shubhangi Hora, Anshu Kumar) and for pandas: Pandas 1.x Cookbook Second Edition(Matt Harrison, Theodore Petrou). all the books I mentioned are fundamentally the best to get on well with them because I found them very practical and useful in the world of machine learning. Hope you can get the most out of them, break a leg!!
"Foundations of Machine Learning" by Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar:
- This book covers the theoretical foundations of machine learning, providing a rigorous treatment of various algorithms and concepts.
"Machine Learning Yearning" by Andrew Ng:
- While not a traditional textbook, this book by Andrew Ng is a practical guide that focuses on the engineering side of machine learning. It provides insights and best practices for building effective machine learning systems.
"The Elements of Statistical Learning" by Trevor Hastie, Robert Tibshirani, and Jerome Friedman:
- Often referred to as "ESL," this book is a comprehensive resource covering statistical learning methods. It's more advanced and assumes a solid understanding of statistics.
"Introduction to Machine Learning" by Alpaydin:
- Ethem Alpaydin's book is a well-structured introduction to machine learning, covering a broad range of topics from basic concepts to more advanced techniques.
"Pattern Recognition and Machine Learning" by Christopher M. Bishop:
- This book provides a comprehensive introduction to the field of pattern recognition and machine learning. It covers fundamental concepts and algorithms with a strong emphasis on probabilistic graphical models.
I had some challenges concerning which book to use for Machine Learning. I finally landed this great material, Dive Into Deep Learning by ASTON ZHANG, ZACHARY C. LIPTON, MU LI, AND ALEXANDER J. SMOLA. This book is fantastic and gives a clear road map from basics to advanced levels; with both theory and "from scratch" code implementation for most of these algorithms.The library used is pytorch. It has been adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge. The material is also open source and also you can visit the website https://d2l.ai/ for more information.
- Badges
- Science topic
- Similar topics
- Social Science
- Media
- Social Media