Introduction to Machine Learning for the Sciences
by Titus Neupert, et al.
Publisher: arXiv.org 2021
Number of pages: 80
Description:
This is an introductory machine learning course specifically developed with STEM students in mind, written by the theoretical Condensed Matter Theory group at the University of Zurich and the Quantum Matter and AI group at the Delft University of Technology. We discuss supervised, unsupervised, and reinforcement learning.
Download or read it online for free here:
Download link
(4.1MB, PDF)
Similar books
Learning Deep Architectures for AIby Yoshua Bengio - Now Publishers
This book discusses the principles of learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models.
(8500 views)
An Introduction to Statistical Learningby G. James, D. Witten, T. Hastie, R. Tibshirani - Springer
This book provides an introduction to statistical learning methods. It contains a number of R labs with detailed explanations on how to implement the various methods in real life settings and it is a valuable resource for a practicing data scientist.
(10467 views)
Machine Learning for Data Streamsby Albert Bifet, et al. - The MIT Press
This book presents algorithms and techniques used in data stream mining and real-time analytics. Taking a hands-on approach, the book demonstrates the techniques using MOA, allowing readers to try out the techniques after reading the explanations.
(7098 views)
Algorithms for Reinforcement Learningby Csaba Szepesvari - Morgan and Claypool Publishers
We focus on those algorithms of reinforcement learning that build on the theory of dynamic programming. We give a comprehensive catalog of learning problems, describe the core ideas, followed by the discussion of their properties and limitations.
(8332 views)