- Concrete Mathematics: A Foundation for Computer Science (great generic initial approach)
- A Programmer's Introduction to Mathematics (good introduction to several topics, but I personally see too little relation with a programming approach and mindset)
- Numerical Methods TOCHECK
- What Is Mathematics? An Elementary Approach to Ideas and Methods (provides rich introduction to different main mathematical topics, with both examples and historical anecdotes. Tends more towards formal proofs and definitions than to intuitive overview and practical examples)
- Basic Mathematics TOCHECK
- Calculus Made Easy - Silvanus P. Thompson
- Mathematical Notation: A Guide for Engineers and Scientists TOCHECK
- Everything You Always Wanted To Know About Mathematics TOCHECK
- No Bullshit Guide to Linear Algebra by Ivan Savov (good introduction also going into details. Provides practical examples from other disciplines)
- Practical Linear Algebra: A Geometry Toolbox (linear algebra in a geometric and algorithmic way, through multiple practical and intuitive examples)
- The Manga Guide to Linear Algebra (lovely introductory book, covering the main basic aspects with examples and clear intuitions)
- Linear Algebra and Its Applications by David Lay (well structured and rich, with proofs and plenty of examples)
- Linear Algebra Done Right (Beyond Euclidean spaces and matrices, focusing on abstract vector spaces and linear maps. Pure textbook style and mathematical formalization, very little practical examples and intuitive explanations)
- Introduction to Linear Algebra, Fifth Edition (2016) (more formal approach)
- Linear Algebra and Its Applications by Gilbert Strang (more introductory and accessible than the other book by the same author, though feels poorly structured)
- Linear Algebra: What You Need to Know (goes more into formal aspects and mathematical proofs)
- Linear Algebra Review and Reference - cs229 Stanford TOCHECK
- Numerical Linear Algebra TOCHECK
- Practical Linear Algebra for Data Science TOCHECK
- Think Stats 2e - Allen B. Downey (Python, good intuitive explanation of basic concepts, often from a different POV compared to other more technical books about statistics)
- Think Bayes (Python, many good concrete examples that can be easily implemented and solved from scratch, greatly helps to absorb Bayes's Theorem and related concepts at a more intuitive level. A bit of interdependency between chapters with code written/presented in previous ones)
- OpenIntro Statistics 3rd Edition (exercises and inline questions with solutions)
- Review of Probability Theory - cs229 Stanford
- Probability Theory: The Logic of Science (very technical and detailed. Probably good if you want to properly refine your knowledge, otherwise previous books provide more approachable and standard content)
- An Introduction to Statistical Learning (R)
- The Elements of Statistical Learning 2 (highly technical)
- The Manga Guide to Statistics
- Bayesian Data AnalysisThird edition TOCHECK
- Bayesian Statistics the Fun Way TOCHECK
- The Art Of Probability - For Scientists And Engineers TOCHECK
- Statistics by Robert S. Witte TOCHECK
- Naked Statistics: Stripping the Dread from the Data TOCHECK
- Statistical inference for data science - Online Book TOCHECK
- Time Series Analysis - Hamilton
- Introductory Time Series with R (Use R!) - Cowpertwait and Metcalfe
- Time Series Analysis and Its Applications: With R Examples - Shumway and Stoffer
- Introduction to Time Series and Forecasting - Brockwell and Davis
- Machine Learning - Tom Mitchell - 1997 (A must #1)
- Pattern Recognition and Machine Learning by Christopher M. Bishop (A must #2)
- Applied Predictive Modeling TOREAD
- Model-Based Machine Learning TOCHECK
- Python Machine Learning - Sebastian Raschka TOREAD
- Hands-On Machine Learning with Scikit-Learn and TensorFlow TOCHECK
- The Hundred-Page Machine Learning Book (very well written, with extensive coverage of relevant topics while being succinct and intuitive. A bit less organized in the last chapters.)
- Machine Learning Engineering by Andriy Burkov TOCHECK
- Probabilistic Machine Learning: An Introduction TOREAD
- Patterns, predictions, and actions: A story about machine learning TOREAD
- deeplearningbook (highly technical, also overview and details about many prerequisites to machine learning, like linear algebra and probability)
- neuralnetworksanddeeplearning - Michael Nielsen (online) (great intuitive look into neural-networks properties and deep-learning models working mechanisms)
- Deep Learning with Python - François Chollet (great intuitive description of the fundamentals of deep learning, both in term of methods and components. Relevant Keras code and references for each section)
- Generative Deep Learning (good high-level coverage of generative models, supported by code examples in Tensorflow 2.0)
- Dive into Deep Learning - An interactive deep learning book TOCHECK
- Deep Learning with PyTorch see also Sebastian Raschka review TOCHECK
- The Mathematical Engineering of Deep Learning TOCHECK
- Python Cookbook, 3rd Edition by David Beazley; Brian K. Jone (great collection of advanced recipes, tips and techniques)
- The Pragmatic Programmer: From Journeyman to Master (fantastic overview of best practices and mindset to make life as a programmer as easy, fruitful and pain-free as possible)
- Practical Python Programming (Online)
- 3blue1brown (Video Series) (Pure math entertainment. Stunning visuals and explanations for many concepts, from linear algebra to physics)
- Advanced Machine-Learning Courses
- AtHomeWithAI - DeepMind Curated Resource List
- AI Curriculum
- End-to-End Machine Learning Library a rich list of resources and links for multiple DS related topics
- fastai - courses, books, library
- Computational Linear Algebra for Coders (Jupyter, actual implementation + optimization considerations for many major statistical procedures like PCA, SVD, etc.)
- Statistics @ Udacity
- Computational Probability and Inference @ edX (Python based) TODO
- Machine Learning by Andrew Ng @ Coursera (de facto standard obligatory introductory course)
- Machine Learning by Georgia Tech
- Neural Networks for Machine Learning @ Coursera TODO
- Deep Learning A-Z™: Hands-On Artificial Neural Networks TODO
- Machine Learning For Coders @ Fast.ai TODO
- AWS Machine Learning Course TODO
- TensorFlow Developer Certificate program TOCHECK
- PyTorch Fundamentals TOCHECK
- CS231n Convolutional Neural Networks for Visual Recognition
- Practical Deep Learning For Coders, Part 1 (entertaining, great view of SOA results, notebooks and great tips on code)
- Practical Deep Learning For Coders, Part 2 TODO
- Deep Learning by Google @ Udacity
- Creative Applications of Deep Learning with Tensorflow @ Kadenze (good interactive examples and exposition, some specific topics not generally found in other courses, otherwise usual CNN and RNN pass)
- Creative Applications of Deep Learning with TensorFlow II
- Deep Learning by Andrew Ng @ Coursera TODO
- TensorFlow in Practice Specialization @ Coursera TODO
- Standford Deep Generative Models CS236 - Fall 2019
- GANs in computer vision - Introduction to generative learning
- Berkeley Deep Unsupervised Learning Spring 2020
- Generative Adversarial Networks (GANs) @ Coursera TODO
- Deep Learning for Computer Vision - Michigan Online TOCHECK
- Yann LeCun’s Deep Learning Course at CDS TOCHECK
- Introduction to Computer Vision @ Udacity (detailed and entertaining presentation of the fundamentals of computer vision)
- Hadoop Platform and Application Framework @ Coursera
- Intro to Hadoop and MapReduce @ Udacity
- Machine Learning With Big Data @ Coursera (brief generic intro to machine learning, practical examples for Spark and KNIME)
- Spark Fundamentals 1 (poorly taught, monotonous reading of slides, non relevant quizzes)
- Generative Art and Computational Creativity @ Kadenze (clear overview and exploration of relevant artistic artifacts for different major topic: chaos theory, rule-based system, grammars, markov chains, agents, artificial-life. Coverage of both visual and audio media. Assignments in MAX)
- Interactive 3D Graphics @ Udacity (introductions to many fundamentals of 3D Graphics while playing around with concrete examples and code in three.js)
- Introduction to Programming for the Visual Arts @ Kadenze TODO
- Procedural Modelling @ edx TOCHECK