With further time spent at home looming, we have gathered 20 resources which are free to access for your continued learning. The below list includes free e-courses & e-books.
A self-study guide for aspiring machine learning practitioners. Machine Learning Crash Course features a series of lessons with video lectures, real-world case studies, and hands-on practice exercises with over fifteen hours of accessible education. Access the course here.
In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Join Andrew NG and his team on this course here.
This open source video lecture series includes 23 full-length seminars, starting with an introduction and scope, later going on to cover topics including rule-based expert systems, neural networks, felicity conditions and more. You can access the lectures from MIT here.
Hugo's open source YouTube based video lectures are a few years old now, but the content is still extremely valuable. Broken up into bitesize and digestible chunks, Hugo starts with the basics and walks viewers through some of the more technical aspects of Neural Networks. See the lecture series here.
This course will introduce you to the basics of AI. Topics include machine learning, probabilistic reasoning, robotics, computer vision, and natural language processing. The course includes relevant industry content and is aimed at those with an 'intermediate' understanding. Read more on the course here.
This course is for experienced C programmers who want to program in C++. The examples and exercises require a basic understanding of algorithms and object-oriented software. Skills gained on this course include Graph Theory, C++11, C++ and Graph Algorithms. See more on the course here.
This course will introduce you to the field of computer science and the fundamentals of computer programming. CS101 is specifically designed for students with no prior programming experience, and touches upon a variety of fundamental topics. This course uses Java to demonstrate those topics. You can access the 52 hour course here.
This extensive list of resources is broken into several sections, including an introduction to RL, algorithm documents, utilities documents and more. The compartmentalised course is great for everyone from beginners to those who need to brush up on their theoretic knowledge. See more here.
This course includes six chapters, starting with an introduction to AI, moving through problem solving, real-world AI, ML, Neural Nets and more. Each chapter is made up of several exercises which will test your understanding of the theoretical learning. You can read more on the course here.
This course covers a wide range of tasks in Natural Language Processing from basic to advanced: sentiment analysis, summarization, dialogue state tracking, to name a few. Upon completing, you will be able to recognize NLP tasks in your day-to-day work, propose approaches, and judge what techniques are likely to work well. The final project is devoted to one of the most hot topics in today’s NLP. View more on the course here.
Free e-books covering AI
Allen B. Downey
Think Stats emphasizes simple techniques you can use to explore real data sets and answer interesting questions. The book presents a case study using data from the National Institutes of Health. Readers are encouraged to work on a project with real datasets. You can access your free copy here.
This guide follows a learn-by-doing approach. Instead of passively reading the book, Ron encourages you to work through the exercises and experiment with the Python code provided. The textbook is laid out as a series of small steps that build on each other until, by the time you complete the book, you have laid the foundation for understanding data mining techniques. You can see more on the textbook here.
Kent D Lee
This clearly written textbook provides an accessible introduction to the three programming paradigms of object-oriented/imperative, functional, and logic programming. Highly interactive in style, the text encourages learning through practice, offering test exercises for each topic covered. You can see more information on this textbook from Kent Lee here.
This eBook is available in both English and German, covering 5 parts, starting with the history and realization of Neural Models and ending with Unsupervised learning Network Paradigms. Read more on the content of this eBook here. You can also download your free version in pdf format here.
David L. Poole and Alan K. Mackworth
Over sixteen chapters, David and Alan cover supervised machine learning, multiagent systems, planning and certainty and more. This eBook is free to view but if used, please consider buying the works to support the authors. You can read more on the foundations of AI here.
Alain F. ZuurElena N. IenoErik H. W. G. Meesters
Based on their extensive experience with teaching R and statistics to applied scientists, the authors provide a beginner's guide to R. To avoid the difficulty of teaching R and statistics at the same time, statistical methods are kept to a minimum. The text covers how to download and install R, import and manage data, elementary plotting, an introduction to functions, advanced plotting, and common beginner mistakes. This book contains everything you need to know to get started with R. You can access your free copy here.
Richard Sutton & Andrew Barto
Richard and Andrew list their goal in writing this book was to provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Both authors wanted their treatment to be accessible to readers in all of the related disciplines. For the most part, our treatment takes the point of view of artificial intelligence and engineering. read the PDF copy here.
Thomas Witelski & Mark Bowen
This book presents mathematical modelling and the integrated process of formulating sets of equations to describe real-world problems. Thomas and Mark describe methods in this book for obtaining solutions of challenging differential equations stemming from problems in areas such as chemical reactions, population dynamics, mechanical systems, and fluid mechanics. Access this book via the springer website here.
Adrian Kaehler & Gary Bradski
Learning OpenCV is a great addition to the list, focussed on Computer Vision in C++ with the OpenCV Library, introducing computer vision and demonstrating how you can quickly build applications that enable computers to see and make decisions based on that data. It is thoroughly updated to cover new features and changes in OpenCV 3.0. See more on this book here.
Ian Goodfellow, Yoshua Bengio & Aaron Courvile
Written by some of the leading minds in the space, this Deep Learning PDF offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. You can access this for free here.
Have we missed any blatant inclusions? Let me know for our next instalment - [email protected]