Tasks in machine learning
Of course, this is not a full list of all areas of machine learning.
Methods of machine learning
Again, many methods did not make it onto this graphic.
Topics in theoretical deep learning
Again, I make no claim to completeness for the topics listed here.
Where my research fits
Color and position of an article correspond to its main focus. There are additional dependencies and connections between the articles, only some non-obvious ones are highlighted. For full article names, links and collaborators, please see my list of publications.
Some connections between deep learning theory and other fields
Many additional connections can be made to stochastic analysis, image processing, computational complexity theory, ... There is a certain bias towards my own perspective and research in this graphic. In general, topics relating to probability and statistics are green, analysis is blue and geometry is purple.
High quality image files, license and tex files
All images on this page are available under a non-commercial CC license (see below). Specifically, you are welcome to share and modify the images for non-commercial use, as long as you attribute them to the original source and grant the same benefit to other users. Non-commercial includes educational purposes at not-for-profit institutions (including public and private institutions), but not at for-benefit institutions or on for-profit websites.
To create your own version of the mind maps, you can find code for a version here. It is based on this example created by Stefan Kottwitz. I understand that my presentation is based on my personal approach to deep learning, so if you create a new version, I would be very grateful if you could reach out and share it with me.
Full resolution versions of all images are available here.