Understanding Machine Learning: From Theory to Algorithms
This textbook contains both an introduction to machine learning and the main learning techniques, which can be suitable for graduate students, and advanced chapters suitable for researchers intending to gather a deeper theoretical understanding.
The first part of the book, in facts, aims at providing a rigorous, yet easy to follow, introduction to the main concepts underlying machine learning (What is learning? How can a machine learn? Can we know if the learning process succeeded or failed?, etc.) and presents models and learning rules in order to answer these questions. In the second and third part of the book, it is described a wide variety of learning models, including PAC model, stochastic gradient descent, neural networks, which are more suitable to advanced learners. Finally, the last part of the book is devoted to advanced theory suitable for researchers.
The first part of the book, in facts, aims at providing a rigorous, yet easy to follow, introduction to the main concepts underlying machine learning (What is learning? How can a machine learn? Can we know if the learning process succeeded or failed?, etc.) and presents models and learning rules in order to answer these questions. In the second and third part of the book, it is described a wide variety of learning models, including PAC model, stochastic gradient descent, neural networks, which are more suitable to advanced learners. Finally, the last part of the book is devoted to advanced theory suitable for researchers.
Type:
Book
Area:
Data Analytics, Machine Learning
Target Group:
Advanced
DOI:
https://doi.org/10.1017/CBO9781107298019
Cite as:
Shalev-Shwartz, S. and Ben-David, S., Understanding machine learning: From theory to algorithms, Cambridge University Press, 2014.
Author of the review:
Giulia Cademartori
University of Genoa
You have to login to leave a comment. If you are not registered click here