- Learn Deep Learning, with a focus on computer vision and robotics: Given that you already have basic machine learning skills, I’d suggest following Andrej Karpathy’s computer vision deep learning course. It will teach you deep learning, with a focus on computer vision. If you prefer reading books, both http://deeplearningbook.org and Neural networks and deep learning are quite amazing.
- Read research papers, watch technical talks: You can combine the goal of learning robotics, reinforcement learning while getting familiar with research papers. Deep learning changes fast, so for a lot of things you’ll have to rely on research papers. The Berkeley group is doing awesome stuff in Deep Learning + Robotics. Also, OpenAI is probably the best at deep learning + reinforcement learning.
- Take up a project: There is a lot of dart art / black magic to deep learning. Nitty-gritties that you don’t pay attention to when watching a lecture, but which are crucial to get right for your model to learn anything. So the only solid test of your understanding is going to be whether or not you can create models which work. Following step-by-step instructions doesn’t count as a project.
Feel free to use this community to ask questions if you get stuck while following any of the courses or books, and to discuss research papers and projects.
Happy deep learning!