Today we will be discussing “Free Training Resources for Artificial Intelligence and Machine Learning”. The field of Artificial Intelligence has taken off in recent years. Data science departments are popping up in universities, businesses are investing in AI research, and governments are researching artificial intelligence technology. This is because AI has the potential to revolutionize the world around us. This revolutionary change will be driven by machine learning. Machine learning is one of the most promising technologies of our time, with applications shaping our society by responding to human needs.
Training Resources for Artificial Intelligence and Machine Learning Skills
The demand for artificial intelligence (AI) and machine learning (ML) professionals far outstrips the supply in today’s world of technology. As a result, specializing in one of these fields and earning certifications in them can significantly improve your job prospects. Not everyone has the resources to devote years of their lives to completing years of schooling to obtain a degree or other credentials.
It may no longer be necessary because of the abundance of free educational content available online. There are so many free online courses, tutorials, and guides to choose from that it is easy to get a solid foundation in any of these topics. More than that, you will be able to study at a pace that works for you. There are materials produced by the world’s most prestigious universities and those put together by experts who want to share their expertise with others.
Some of these courses are geared toward people who want to learn how to design and code AI algorithms. In contrast, others are geared toward people looking to put together the growing number of “DIY” AI tools and services or for people who need to oversee AI projects in their organizations. If you are looking to broaden your horizons, chances are you will find something useful here.
The 109 Best Useful Free Online AI And ML Training Resources for 2022
| S. No. | Courses: Artificial Intelligence and Machine Learning | Course Type | Course Description |
|---|---|---|---|
| 1 | 21 Definitions of Fairness and Their Politics | Video lecture | Arvind Narayanan discusses the various definitions of fairness and the tradeoffs they present for society |
| 2 | 3Blue1Brown Youtube channel | Video series | Great tutorial series. Videos on Linear Algebra and Neural Networks from Ground Up are particularly useful |
| 3 | A 2020 vision of Linear Algebra (Gilbert Strang, MIT) | Video series | Concisely summarises a whole course of linear algebra, with technical details, through a new lens: how Linear Algebra is being applied to the real world, especially in Machine Learning. |
| 4 | A Code-first Introduction to Natural Language Processing | Video lectures | An introduction to natural language processing for people with a technical background. |
| 5 | A Primer on Neural Network Models for Natural Language Processing | Paper | A clear review of how neural networks are used in natural language processing. |
| 6 | AGI Safety Literature Review | Paper | Great overview of AGI safety literature up to 2018, with hundreds of references to follow up on. |
| 7 | AI Alignment newsletter by Rohin Shah | Newsletter | Weekly newsletter summarizing recent work in AI safety |
| 8 | AI safety YouTube channel by Robert MIles | Video lectures | Educational and entertaining videos introducing key concepts in AGI safety to a popular audience |
| 9 | Alberta RL 4-course Specialization | Online course | A four-course sequence on RL, starting from Bandits and ending at RL with function approximation (NNs), Policy Gradient methods, and Average Reward. |
| 10 | Amii’s Coursera Machine Learning: Algorithms in the Real World Specialization | Online course | Excellent view into framing and identifying ML problems and their solutions |
| 11 | An overview of gradient descent optimization algorithms | Blog post | A comprehensive blog post that reviews the main variants of gradient descent that are used to optimize neural networks. |
| 12 | Andrej Karpathy blog/hacker guide | Blog post | Very easily accessible intro to neural nets. Also, his blog has very digestible practical advice. |
| 13 | Andrew Ng’s Machine Learning course | Online course | The very hands-on and comprehensive first course for machine learning. Since it is on Coursera, you can have your assignment “graded” and also have TA’s and other peers to help you get through the materials. |
| 14 | Ankur Handa’s blog on Sim2Real | Blog post | Useful posts about simulators, sim2real transfer learning, physics engines |
| 15 | Bayesian Reasoning and Machine Learning | Online book | Basics of probabilistic reasoning and modeling |
| 16 | Brain Inspired Podcast | Podcast | A podcast where neuroscience and AI converge. |
| 17 | Causal Inference in Statistics: A Primer | Online preprint | Excellent introduction into causal inference. This is a preprint but complete version of the final book. |
| 18 | Causal Inference: What If | Online book | New book on causal inference |
| 19 | Center for Brains Minds + Machines Summer School Lectures | Video series | Lectures from famed Woods Hole summer school on computational *cognitive* neuroscience (aka more about high-level cognition, behavior, links to machine learning) |
| 20 | Chelsea Finn’s Multi-Task and Meta-Learning Course | Video lectures | Video lectures on multi-task and meta-learning |
| 21 | Chris Olah blog | Blog posts | Chris Olah has a very educational approach for exampling key concepts (such as understanding converts or lstms) in machine learning in an in-depth manner. Olah is passionate about education and does a fantastic job putting his posts together. |
| 22 | Computational Cognitive Modeling @ NYU | Lecture slides & readings | An overview of computational approaches to modeling human cognition, with close ties to artificial intelligence and machine learning. |
| 23 | Computational models of the neocortex | Class notes | Very interdisciplinary and cutting edge |
| 24 | Concrete Problems in AI safety | Paper | A useful overview of AI safety problems, the original and now classic paper for the field of AI safety |
| 25 | Crash Course AI | Video series | Useful, well-produced intro series, probably best for high schoolers and novices? |
| 26 | Natural Language Processing with Deep Learning | Video lectures Video lectures |
Stanford’s course on state-of-the-art natural language processing. Wonderful class notes here: https://cs231n.github.io/ A good continuation of Andrew Ng’s course that dives much deeper into convolutional neural networks (that was briefly touched on at the end of the previous course) and introduces |
| 27 | CS231n: Convolutional Neural Networks for Visual Recognition (Stanford’s legendary CNN lectures) | Video lectures | Provides a great overview of classical and more recent work on convnets which build the foundation for much most work with visual data. |
| 28 | CS330: Meta learning and Multitask | Video lectures | Provides an overview of recent work in meta-learning and multitask learning. Inspiring and very useful to keep up to speed with recent ideas in these fields. |
| 29 | David MacKay, information theory course videos | Video lectures | Covers a broad set of areas in MacKay’s Feymanesque lecturing style |
| 30 | David MacKay, all video lectures | Video lectures | David MacKay is a well-known name in the field, particularly focusing on statistics and probabilistic machine learning. |
| 31 | David MacKay, Gaussian Process Basics | Video Lecture | This is the most accessible and clear introduction to Gaussian Processes around! |
| 32 | David MacKay’s book “Information Theory, Inference, and Learning Algorithms” | Book | David MacKay offers a unique perspective on the connections between information theory, inference, and learning. His writing style is unique in its style and humour1 |
| 33 | David MacKay’s Course on Information Theory, Pattern Recognition, and Neural Networks | Video lectures | A course on Information theory, pattern recognition, and neural networks by the legendary David MacKay |
| 34 | David Silver, Introduction to Reinforcement Learning | Video lectures | Covers ideas in Sutton’s and Barto’s textbook with a very good flow: Why should we think about these problems? How do the ideas we discussed so far relate to one another? etc. |
| 35 | David Silver’s RL Course from UCL | Video lectures | Useful for anyone wanting to learn about RL |
| 36 | Decision-theoretic foundations for statistical causality | Online article | An alternative way to formulate causal inference operations |
| 37 | Deep Bayes summer school lectures and lab materials | Video lectures | Lectures and practicals on probabilistic modeling and Bayesian learning |
| 38 | Deep Learning at Oxford 2015 | Video lectures | Oxford’s course on Deep Learning in 2015. |
| 39 | Deep Learning Book | Book | A comprehensive introduction to the fundamentals of Deep Learning by some of the pioneers in the field. |
| 40 | Deep Learning Indaba Practicals | Colabs | There are guided tutorials developed and tested over many years to train people in Deep Learning, from the fundamentals up to advanced topics like building an auto diff framework or training a GAN. |
| 41 | Dive into Deep Learning | Book | Great format, which makes learning key ML concepts more fun and interactive. |
| 42 | DL + RL course with UCL | Video lectures | This course covered a lot of ground on deep learning and reinforcement learning. It consisted of two, mostly separate, tracks: one on DL and one on RL, which can be consumed separately. |
| 43 | EEML (first/second edition) Lab materials | Colab | Lab material for EEML summer school, covering topics like vision, RNN, unsupervised learning, and RL. The material come in the form of exercises with solutions supposed to help introduce a lot of basic ideas |
| 44 | EEML slides from lectures | Slides | Slides for the lectures from the previous year’s edition of EEML (unfortunately no recordings). This covers a great set of material from intro material to more complex presentations. |
| 45 | Elements of Causal Inference: Foundations and Learning Algorithms | Online book | This book introduces the reader to causal inference in a simple and accessible way. |
| 46 | Emma Brunskill RL Course | Video lectures | Video lectures on reinforcement learning from Emma Brunskill’s course at Stanford. |
| 47 | Ermon’s graphical models course at Stanford | Lectures notes | Covers a lot of probabilistic methods |
| 48 | Essence of Linear Algebra (3blue1brown) | Video series | Provides very good *intuition* into the key ideas of linear algebra, without going too much into the technical details. Accompanies a traditional linear algebra textbook or college course. |
| 49 | Fairness and Machine Learning Book | Book, Video Lectures | Overview of Fairness in Machine Learning Topics |
| 50 | Francis Bach’s blog | Blog | Useful tricks and tips, insightful analysis of various machine learning concepts |
| 51 | Full Stack Deep Learning | Online Course | Deep learning models do not live in a vacuum. This course highlights the practical aspects of deep learning such as model deployment, infrastructure, debugging, and even preparing for deep learning interviews. |
| 52 | Getting into machine learning | Blog | A blog for those looking to get into machine learning |
| 53 | Good resource for learning foundations of computer science | Online course | Provides high-quality, live, interactive computer science classrooms. Code.org is a nonprofit dedicated to expanding access to computer science in schools and increasing participation by women and underrepresented youth. |
| 54 | Goodman (1955). The New Riddle of Induction | Book chapter | Philosophical background on inductive bias and why inferences and induction are hard. |
| 55 | Harvard University’s Justice Course | Video lectures | In-depth and engaging lecture series on justice and moral philosophy. |
| 56 | How to Use t-SNE Effectively | Interactive textbook | It provides an interactive, insightful journey into all the major pitfalls of using tSNE, which has become one of the most commonly used low-dimensional data embeddings. I found it extremely useful to better understand what one can really |
| 57 | Human Compatible: Artificial Intelligence and the Problem of Control by Stuart Russell | Book | Must-read book on AI safety by an AI pioneer |
| 58 | Human intelligence enterprise course | Course materials | History of human intelligence |
| 59 | Intro to machine learning talk at Lviv workshop | Video lecture | Introduction to machine learning. It introduces some theories on which one can build the machinery of deep learning |
| 60 | Is the Abstract Mathematics of Topology Applicable to the Real World? | Video series | The introduction is a great description of the basics of topology. The seminar goes on to describe certain applications in a really compelling way |
| 61 | KhanAcademy courses | Online course | Great introductions for beginners into Statistics, Probability Theory, Calculus, necessary to understand ML. |
| 62 | Khipu videos and practicals | Videos of lectures, slides, and collabs | Resources from Khipu, including videos and practicals that students can go along with. |
| 63 | Learning from Data course – Caltech | Video lectures | Gentle introduction to Machine Learning. Topics are explained very clearly. |
| 64 | Lecture notes on Machine Learning | Lecture Notes | Lecture notes from Herbert Jaeger’s machine learning course. Covering a lot of the basics and standard ML topics. Written very well (almost like a book). |
| 65 | Lecture Notes on Monte Carlo | Lecture Notes | A short tutorial on the Monte Carlo method |
| 66 | Lectures from Methods in Computational Neuroscience Woods Hole Summer School | Video series | Lectures from famed Woods Hole summer school on computational *systems* neuroscience (aka more about circuits and system properties of the brain) |
| 67 | Lex Fridman’s AI podcast | Podcast | Conversations with a diverse and impressive set of guest speakers. |
| 68 | Lilian Weng’s blog | Survey blog posts | Lilian’s blog provides overview blog posts for various fields from curriculum learning, self-supervised learning, meta-learning etc. The blogposts are not too detailed and sometimes a bit specialized but are quite often even updated to |
| 69 | Machine Learning at UBC 2012 | Video Lecture | UBC’s course on Machine Learning in 2012. |
| 70 | Machine Learning, Probability and Graphical Models (Sam Roweis) | Video Lectures | A clear explanation by the legendary Sam Roweis on graphical models. |
| 71 | Marr’s Levels of Analysis (Vision, 1982, Chapter 1) | Book chapter | The book chapter describes Marr’s “Levels of Analysis” (1982), which are an important framework for thinking about intelligent systems. |
| 72 | Mathematicalmonk Youtube videos | Video lectures | Incredibly well explained, goes into examples for useful algorithms such as EM. Good as an additional resource to a book like Bishop. |
| 73 | Mathematics for Machine Learning | Book | A great book that covers basic mathematical concepts needed to do machine learning |
| 74 | Mike Bostock interactive visualizations | Live Code | Mike Bostock’s interactive visualizations |
| 75 | MIT 6.S191 Intro to Deep Learning | Videos, tutorials, assignments. | MIT’s introductory course on deep learning and applications. |
| 76 | MIT Brains, Minds, and Machines Summer Course | Video lectures, tutorials, projects | A graduate-level course at the intersection of cognitive science, neuroscience, and AI |
| 77 | MIT Machine Learning course | Online course with lecture videos, problem sets, solutions, and exams. | Taught in 2006, a great course on the fundamentals (and now history) of machine learning before deep learning and many levels of abstractions became the mainstream. |
| 78 | Monte Carlo Gradient Estimation in Machine Learning | Paper | Useful for anyone doing RL or generative modeling. |
| 79 | Nando de Freitas Course on Machine Learning | Video lectures and slides | A helpful course on machine learning & the slides that go along with it. |
| 80 | NeurIPS 2017 Tutorial on Fairness in Machine Learning | Video lectures | Solon Barocas and Moritz Hardt provide an in-depth discussion on the sociotechnical elements of Fairness in Machine Learning |
| 81 | NLP Progress Online journal |
List of datasets and results Journal |
A community-driven website that lists a large number of tasks, datasets, and state-of-the-art results in natural language processing. Peer-reviewed online journal, allows informative visualizations and code to be included, to facilitate understanding of research works and improve transparency and reproducibility |
| 82 | OpenAI blog Oxford/DM NLP Course 2017 |
Blog Lecture course |
Accessible presentations of basic and advanced algorithms for RL An advanced lecture course on NLP delivered in Oxford by DeepMinders |
| 83 | Parallel Distributed Processing | Online book | A classic for anyone who wants to understand the roots of deep learning, back when it was “connectionism.” |
| 84 | Practical Deep Learning for Coders | Online course | Recommended by friends from another technical background (such as physics and maths) as a great entry course to Deep Learning |
| 85 | Princeton Companion to Mathematics | Book | Probably the most amazing maths resource you will ever find. This book provides a thorough overview of the most important concepts in modern mathematics, assuming no background knowledge, and in the self-proclaimed ‘bedtime story’ |
| 86 | Probabilistic Models of Cognition | Interactive textbook | An interactive textbook describing how to use probabilistic models to produce and model human-like behavior. |
| 87 | Probability in high dimensions | Lecture Notes | A very readable book “of ideas at the intersection of probability, analysis, and a geometry that arise across a broad range of contemporary problems in different areas.” |
| 88 | Project Euler | Problem Solving Community | A series of challenging math + CS problems to stimulate the brain. They are super fun and will lead you to learn things that will help your deep learning career down the road. |
| 89 | Ranking of ML online courses | Reading list | Quite a comprehensive overview of most of the top online courses on machine learning. |
| 90 | Reinforcement Learning: an Introduction (2018 edition) | Book | This is *the* introductory book of reinforcement learning. Rich does an amazing job at explaining both the fundamental concepts of RL as well as guiding the reader through all the way to advanced open research problems. |
| 91 | Reproducing kernel Hilbert spaces in Machine Learning | Course materials | Useful for anyone interested in generative modeling and beyond. |
| 92 | Speech and Language Processing | Book | The authoritative reference on natural language processing is now in its 3rd version and available online. |
| 93 | Spinning Up in Deep RL | Code | This is an educational resource produced by OpenAI that makes it easier to learn about deep reinforcement learning (deep RL). |
| 94 | Stanford Physics lecture series by Leonard Susskind | Video lectures | A great resource for learning many important areas of modern physics, including classical, statistical, and quantum mechanics. These lectures assume very little background knowledge, and Leonard is able to introduce and explain complex |
| 95 | Stanford’s Machine Learning Course | Video lectures | Introduction to machine learning course |
| 96 | Stanford’s NLP with Deep Learning Course | Online course | Useful for anyone who wants to get into NLP |
| 97 | Statistical Learning Theory course | Online course | A free course, led by professors Hasti and Tibshirani, covers a lot of basics of machine learning, oriented towards people with more mathematical backgrounds. |
| 98 | Strang All the Key Ideas of Linear Algebra in 1 Lesson | Video lecture | Concise, integrative |
| 99 | Strogatz nonlinear dynamics course | Videos | Video courses on nonlinear dynamics |
| 100 | Sunday Classics | Reading list | A collection of classical papers on all topics in machine learning, cognitive science, statistics, information theory, neuroscience, artificial intelligence, signal processing, operations research, econometrics, and others. |
| 101 | Sutton and Barto’s Reinforcement Learning | Textbook | This is THE textbook for RL. It builds up from very fundamental concepts to advanced topics. Accompanies David Silver’s lectures. |
| 102 | The Annotated Transformer | Blog post | An excellent introduction to the dominant NLP model |
| 103 | The Book of Why | Book chapters | Light introduction into causal inference and historical excursion on its development |
| 104 | The challenge of understanding the brain: where we stand in 2015 | Paper | Good overview of the more circuit/biology end of neuroscience |
| 105 | The Trouble with Bias – NeurIPS 2017 | Video Lecture | Kate Crawford discusses the ethical implications of bias in AI systems |
| 106 | Theoretical Neuroscience | Online book | the popular introductory text of theoretical neuroscience |
| 107 | U of A / Amii Coursera RL Specialization by White and White | Online courses | Made by UofA / Amii, a heartland of RL research; Adam White is a DeepMinder; comprehensive and well-designed course series that will give the most important fundamentals of RL |
| 108 | Variational inference a review for statisticians by David Blei | Paper | Provides the best explanation for VI in the context of generative modeling that I have seen. |
| 109 | WEKA: a workbench for machine learning | Online resource | A large, free software toolset for getting to know data, data visualization, classification, regression, feature selection, and the foundations of data science; I use this regularly to teach others how to see the patterns in data and appreciate |
