*This list will be updated. *
Types of tutorials:
📺 Videos
📙 Books
📄 Documents and blog posts
Machine Learning
📙 Oliver Theobald : Machine leanring for absolute beginners
This 200-page long book gives you a general idea about machine learning and the different types of algorithms used in statistical learning. It is not a must, but not bad to have a look at.
📺 Andrew Ng : machine learning course
This course starts from the basics of ML and then enters deep learning by explaining the neural networks and finally it goes to unsupervised learning methods. Also, this course includes some tips and tricks for making the ML systems. It is a must! Anyone who wants to start the ML should begin with this course.
📺 IBM : applied machine learning with python
This course is relatively short. It teaches how to use libraries like NumPy and sci-kit learn for implementing ML algorithms. It is a good start for learning how to code ML algorithms in python.
Deep Learning
📺 Deeplearning.ai : Deep learning specialization
This specialization consists of 5 courses each about 4 weeks. The first course is an introduction to Neural networks, the second is about technical details of neural networks and how to make them work better, the third course is about managing ML projects and how to find errors in your work, the fourth course includes convolutional neural networks and concepts of computer vision with deep learning, and final course is about natural language processing with deep learning. This is specialization is probably the best video tutorial on the internet. Along with the theory, you also learn how to TensorFlow library for implementing the deep learning algorithms.
📺 Stanford CS213N: Convolutional Neural Networks for Visual Recognition
This is a recording of Stanford's CS231n class. It can be used as a complementary course with course 4 of Deeplearning.ai. You can watch this course to learn about some concepts like Generative Adversarial Networks that are not covered in the Deeplearning.ai course.
📺 Stanford CS224N: NLP with Deep Learning
This is a recording of Stanford's CS224n class. this course can be used as a complementary course with course 5 of Deeplearning.ai. You can watch this course to learn about some concepts like Transformer networks that are not covered in the Deeplearning.ai course.
📺 Stanford CS234: Reinforcement Learning
This is a recording of Stanford's CS234 class. It is a great introduction to reinforcement learning, which is not covered at all in Deeplearning.ai specialization.
📺 fast ai : deep learning for coders
This course is mostly practical. The tutors do not focus on the theory and math involved in DL. By watching this course you can learn about the PyTorch library and an easy-to-use API library which is called FastAi library and it is based on PyTorch. The tutors teach some useful tips and tricks about training the neural networks.
📺 deeplearning.ai : TensorFlow Specialization
It is a relatively simple course. It focuses on implementing fundamental concepts of deep learning with Keras which is a library based on TensorFlow. There isn't much theory in this specialization and it is mostly about implementing algorithms with Keras.
📺 deeplearning.ai : TensorFlow Data and Deployment
In this four-course Specialization, you’ll learn how to get your machine learning models into the hands of real people on all kinds of devices. Start by understanding how to train and run machine learning models in browsers and in mobile applications.
Math and more theory!
📙online DL book-deeplearningbook
This a comprehensive book on deep learning, which starts with a quick review of the math that you need for deep learning. I don't suggest starting with this book, but after you went through some of the courses that I mentioned above, you start studying this book. The concepts are explained in-depth in this book.
📺 Mathematics for Machine Learning Specialization
This specialization starts with Linear Algebra and goes toward some statistics and calculus. It starts from the foundations and it is not that hard to follow. It gives a good introduction to the math that is behind the ML and DL algorithms. It is a good idea to watch this course after watching deeplearning.ai specialization.
📺 MIT 18.06 Linear Algebra
Amazing course on linear algebra taught by Prof Gilbert Strang. Very easy to follow, and covers the principles of what you need to know from LinALg.