概率机器学习：进阶 谷歌研究科学家 Probabilistic Machine Learning : Advanced Topics

基本信息

Format:Hardback 1360 pages, 350 COLOR ILLUS.

Publisher:MIT Press Ltd

Imprint:MIT Press

ISBN:9780262048439

Published:15 Aug 2023

Weight:2312g

Dimensions:213 x 237 x 55 (mm)

页面参数仅供参考，具体以实物为准

书籍简介

一本高级书籍，面向从事机器学习和统计学工作的研究人员和研究生，他们想要学习深度学习、贝叶斯推理、生成模型和不确定性下的决策。

作为《概率机器学习:导论》的高级版本，这本高水平的教科书为研究人员和研究生提供了机器学习前沿主题的详细介绍，包括深度生成建模、图形模型、贝叶斯推理、强化学习和因果关系。本卷将深度学习纳入更大的统计背景，并将基于深度学习方法与基于概率建模和推理的方法统一起来。这本严谨的书由来自谷歌、DeepMind、亚马逊、普渡大学、纽约大学和华盛顿大学等地的科学家和领域专家共同撰写，对于理解机器学习中的重要问题至关重要。

•涵盖高维输出的生成，如图像，文本和图形

•讨论了基于潜在变量模型发现数据洞察力的方法

•考虑不同分布下的训练和测试

•探索如何使用概率模型和推理进行因果推理和决策

•功能在线Python代码伴奏

An advanced book for researchers and graduate students working in machine learning and statistics who want to learn about deep learning, Bayesian inference, generative models, and decision maki making under uncertainty.

An advanced counterpart to Probabilistic Machine Learning: An Introduction, this high-level textbook provides researchers and graduate students detailed coverage of cutting-edge topics in machine learning, including deep generative modeling, graphical models, Bayesian inference, reinforcement learning, and causality.  This volume puts deep learning into a larger statistical context and unifies approaches based on deep learning with ones based on probabilistic modeling and inference.  With contributions from scientists and domain experts from places such as Google, DeepMind, Amazon, Purdue University, NYU, and the University of Washington, this rigorous book is essential to understanding the vital issues in machine learning.

•Covers generation of high dimensional outputs, such as images, text, and graphs

•Discusses methods for discovering insights about data, based on latent variable models

•Considers training and testing under different distributions

•Explores how to use probabilistic models and inference for causal inference and decision making

•Features online Python code accompaniment

作者简介

凯文·帕特里克·墨菲出生于爱尔兰，剑桥大学文学学士，在美国读研究生(宾夕法尼亚大学硕士，加州大学伯克利分校博士，麻省理工学院博士后)。2004年，他成为加拿大温哥华英属哥伦比亚大学计算机科学与统计学教授。2011年，他去了位于加州山景城的谷歌公司休假。2012年，他转行成为谷歌的全职研究科学家。Kevin在评审会议和期刊上发表了50多篇与机器学习和图形模型相关的论文。

Kevin Patrick Murphy was born in Ireland, grew up in England (BA from Cambridge),and went to graduate school in the USA (MEng from U. Penn, PhD from UC Berkeley,Postdoc at MIT). In 2004, he became a professor of computer science and statistics at the University of British Columbia in Vancouver, Canada. In 2011, he went to Google in Mountain View, California for his sabbatical. In 2012, he converted to a full-time research scientist position at Google. Kevin has published over 50 papers in refereed conferences and journals related to machine learning and graphical models.