| layout | title | subtitle |
|---|---|---|
page |
Machine Learning Resources |
General |
Link: https://slds-lmu.github.io/i2ml/
Authors / Institution: SLDS, LMU (B.Bischl, L. Bothmann, F. Scheipl, D. Schalk, T. Pielok, L. Wimmer)
Keywords: machine learning, supervised learning
Description: This website offers an open and free introductory course on (supervised) machine learning. The course is constructed as self-contained as possible and enables self-study through lecture videos, PDF slides, cheatsheets, quizzes, exercises (with solutions), and notebooks.
Reason: Having a resource to turn to for the basic stuff, especially the first four chapters can be used to lay the most important foundations which still remain important even when working with deep neural networks.
Limitations: This course covers mostly “classical” machine learning, no deep learning (i.e. neural networks) or methods specifically tailored to unstructured data.
Link: https://www.youtube.com/watch?v=vT1JzLTH4G4&list=PLSVEhWrZWDHQTBmWZufjxpw3s8sveJtnJ&index=1
Authors / Institution: Stanford University
Keywords: deep learning, deep reinforcement learning, generative models
Description: This course on deep learning is offered by Stanford University and encompasses an introduction to the fundamentals of deep learning, as well as examples of more sophisticated topics, including deep reinforcement learning.
Reason: The presentation of the theory and understanding of deep learning is thorough and the demonstration of its motivational aspects is convincing.
Limitations: The sections of advanced deep learning are covered briefly. For an elaborated and thorough understanding of these topics additional sources are necessary.