Hey!

I'm often asked what are some good resources to study deep learning or machine learning. To answer that here's a list of resources that one can refer to. Also I happen to misplace(sometimes) some of the resources myself :P I plan to make this an open source collection of all courses related to deep learning. It would be great if you would like to contribute to expand this list

For Starters

1. Andrew Ng's course
   I started with this and so did million other people, so yea...... There's a YouTube playlist but I would suggest auditing the course on coursera or asking for coursera aid.
   
2. Fast.ai
   Their course gives head start to people working in industry wanting to use deep learning. Their tutorials are based on the library fastai. The community is super awesome and supportive. Checkout discussions at their forum and discord.
   
3. PyTorch
   Fastai's codebase is based on PyTorch. It's one of the highly used frameworks and has awesome tutorials online with an active community. Most of your questions would already be answered there. If you are exploring that means you wish to create models more intuitively and maybe create custom pipelines.
   
4. NYU - Deep Learning course
   The one of the most popular courses freely available online. I love the visualizations in the blogs and Alfredo's practical tutorials. Another plus point of the tutorial is it's practical. One gets to learn theory along with the syntax and design of the model.
   
5. Intro to Deep Learning
   This is a diverse course, covering a lot of applications of deep learning with concepts.
   

Digging Deeper

1. Designing, Visualizing and Understanding Deep Neural Networks
   

2. Geometric Deep Learning
   This course is based on Michael Bronstein et al's Proto Book which discusses about exploiting lower-dimensional features to study and improve neural networks.
   

3. Probabilistic Machine Learning
   This course provides an introduction to core concepts of machine learning from the probabilistic perspective.
   

   Computer Vision

   1. CS231n Convolutional Neural Networks for Visual Recognition
      This course discusses Convolutional neural networks(CNN) and CNN based models along with varied set of tasks that CNNs can be used to solve.
      
   2. CS231A: Computer Vision, From 3D Reconstruction to Recognition
      This course mostly discusses about 3D computer vision(estimating poses, shapes, etc). They also teach about camera models and stereo vision.
   3. Computer Vision by Prof. Andreas Geiger
      This course will provide an introduction to computer vision, with topics including image formation, camera models, camera calibration, feature detection and matching, motion estimation, geometry reconstruction, object detection and tracking, and scene understanding.
      

   Natural Language Processing

   1. CS224n: Natural Language Processing with Deep Learning
      
   2. Hugging Face NLP Course
      Hugging face is the go-to library for most of the people doing NLP. They have awesome support of datasets, pre-trained model and in this course they cover how to make best use of the library.

   Reinforcement Learning

   1. Reinforcement Learning Course | Deepmind & UCL
      From the link:
      Comprising 13 lectures, the series covers the fundamentals of reinforcement learning and planning in sequential decision problems, before progressing to more advanced topics and modern deep RL algorithms. It gives students a detailed understanding of various topics, including Markov Decision Processes, sample-based learning algorithms (e.g. (double) Q-learning, SARSA), deep reinforcement learning, and more. It also explores more advanced topics like off-policy learning, multi-step updates and eligibility traces, as well as conceptual and practical considerations in implementing deep reinforcement learning algorithms such as rainbow DQN.
      

Books and PDFs

1. Mathematics for Machine Learning
2. Geometric Deep Learning(Proto Book)
3. Machine Learning: A Probabilistic Perspective
4. Approaching(Almost) any machine Learning problem