Probabilistic machine learning : an introduction /
"This book provides a detailed and up-to-date coverage of machine learning. It is unique in that it unifies approaches based on deep learning with approaches based on probabilistic modeling and inference. It provides mathematical background (e.g. linear algebra, optimization), basic topics (e.g...
Saved in:
Main Authors: | |
---|---|
Published: |
The MIT Press,
|
Publisher Address: | Cambridge, Massachusetts : |
Publication Dates: | [2022] |
Literature type: | Book |
Language: | English |
Series: |
Adaptive computation and machine learning series
|
Subjects: | |
Summary: |
"This book provides a detailed and up-to-date coverage of machine learning. It is unique in that it unifies approaches based on deep learning with approaches based on probabilistic modeling and inference. It provides mathematical background (e.g. linear algebra, optimization), basic topics (e.g., linear and logistic regression, deep neural networks), as well as more advanced topics (e.g., Gaussian processes). It provides a perfect introduction for people who want to understand cutting edge work in top machine learning conferences such as NeurIPS, ICML and ICLR"-- |
Carrier Form: | xxix, 826 pages : illustrations (some color) ; 24 cm. |
Bibliography: | Includes bibliographical references (pages [793]-826) and index. |
ISBN: |
9780262046824 0262046822 |
Index Number: | Q325 |
CLC: |
O211 TP181 |
Call Number: | TP181/M978-1 |