What do you think?
Rate this book
Algorithms of the Intelligent Web
Summary Algorithms of the Intelligent Web, Second Edition teaches the most important approaches to algorithmic web data analysis, enabling you to create your own machine learning applications that crunch, munge, and wrangle data collected from users, web applications, sensors and website logs. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the Technology Valuable insights are buried in the tracks web users leave as they navigate pages and applications. You can uncover them by using intelligent algorithms like the ones that have earned Facebook, Google, and Twitter a place among the giants of web data pattern extraction. About the Book Algorithms of the Intelligent Web, Second Edition teaches you how to create machine learning applications that crunch and wrangle data collected from users, web applications, and website logs. In this totally revised edition, you'll look at intelligent algorithms that extract real value from data. Key machine learning concepts are explained with code examples in Python's scikit-learn. This book guides you through algorithms to capture, store, and structure data streams coming from the web. You'll explore recommendation engines and dive into classification via statistical algorithms, neural networks, and deep learning. What's Inside About the Reader Knowledge of Python is assumed. About the Authors Douglas McIlwraith is a machine learning expert and data science practitioner in the field of online advertising. Dr. Haralambos Marmanis is a pioneer in the adoption of machine learning techniques for industrial solutions. Dmitry Babenko designs applications for banking, insurance, and supply-chain management. Foreword by Yike Guo. Table of Contents
- GenresAlgorithmsTechnical
244 pages, Paperback
First published March 2, 2016
3 people are currently reading
47 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 2 of 2 reviews
December 6, 2020
A solid book on various algorithms and procedures associated with business on the web, this book did a fine job not only of providing a non-trivial overview of pertinent algorithms for Web 2.0 companies, but also illustrating those algorithms with respect to applications one may see. The book covers logistic regression, decision trees, PCA, clustering, recommender systems, neural networks, and multi-armed bandits, with relevant variations for each of these algorithms. However, the two standout chapters are on recommender systems and multi-armed bandits (MAB).
All code is written mostly with base Python with some use of sklearn, scipy, and numpy, with some unique libraries/assets covered like VowPal Wabbit which is a unique command line library built in C++, and focused on online learning on some kind of commodity machine for various machine learning algorithms and their helper-procedures (mostly linear algebraic dimensional reduction procedures here). With respect to both recommender systems and MAB, these topics are given very clean conceptual explanations with appropriate nodes to theory when needed (the theory of singular-value decomposition in the former, and the theory of Bayesian distribution learning for the later), and I was impressed by how easy the exposition was in these two chapters. What makes the coverage of this chapter extra special is for more introductory or practitioner texts, one often does not find either topic covered much at all, with the standard purview from these text being on issues of prediction, as opposed to dimensional reduction or experimentation.
With respect to the other sections, I felt enough of the construction of apparatus was explained to give the reader a true understanding of how they worked. So logistic regressions were not just explained as a kind of linear regression, but the exact step-by-step derivation of the link-function and how the algebraic tricks makes it linear was provided. Likewise, the chapters on neural networks are also well taught from a first-principles standpoint. However, because this text was published in 2015 or 2016, there’s a strange absence of TensorFlow from the syntax which marks negatively on the overall text from a more contemporary practitioner’s standpoint. Still, having read this I am pleased with it as a refresher on some topics. I could see this pairing as a textbook in an applied machine learning course, or for a reader first being introduced to the topic, perhaps pairing it with something like Gautam Shroff’s “Intelligent Web� might be appropriate. Although the only connection between that book and this one is that they are roughly thematically centered on web-technologies, that book is more like an introduction to web algorithms from a more general machine learning standpoint. There are some connections in that, although a layman book, Stroff does a decent job of going into some details on classification (precision/recall/tuning etc.), and McIlwraith Et. Al. also covers this, but goes more in detail on how it impacts the life-cycle of these assets from a business standpoint. Definitely a recommend.
All code is written mostly with base Python with some use of sklearn, scipy, and numpy, with some unique libraries/assets covered like VowPal Wabbit which is a unique command line library built in C++, and focused on online learning on some kind of commodity machine for various machine learning algorithms and their helper-procedures (mostly linear algebraic dimensional reduction procedures here). With respect to both recommender systems and MAB, these topics are given very clean conceptual explanations with appropriate nodes to theory when needed (the theory of singular-value decomposition in the former, and the theory of Bayesian distribution learning for the later), and I was impressed by how easy the exposition was in these two chapters. What makes the coverage of this chapter extra special is for more introductory or practitioner texts, one often does not find either topic covered much at all, with the standard purview from these text being on issues of prediction, as opposed to dimensional reduction or experimentation.
With respect to the other sections, I felt enough of the construction of apparatus was explained to give the reader a true understanding of how they worked. So logistic regressions were not just explained as a kind of linear regression, but the exact step-by-step derivation of the link-function and how the algebraic tricks makes it linear was provided. Likewise, the chapters on neural networks are also well taught from a first-principles standpoint. However, because this text was published in 2015 or 2016, there’s a strange absence of TensorFlow from the syntax which marks negatively on the overall text from a more contemporary practitioner’s standpoint. Still, having read this I am pleased with it as a refresher on some topics. I could see this pairing as a textbook in an applied machine learning course, or for a reader first being introduced to the topic, perhaps pairing it with something like Gautam Shroff’s “Intelligent Web� might be appropriate. Although the only connection between that book and this one is that they are roughly thematically centered on web-technologies, that book is more like an introduction to web algorithms from a more general machine learning standpoint. There are some connections in that, although a layman book, Stroff does a decent job of going into some details on classification (precision/recall/tuning etc.), and McIlwraith Et. Al. also covers this, but goes more in detail on how it impacts the life-cycle of these assets from a business standpoint. Definitely a recommend.
February 13, 2020
Niestety tylko 3, ale to nie znaczy, że książka jest zła.
Po prostu jest trudna i wymaga dosyć dużej wiedzy matematycznej,
dużo jest dosyć trudnych wyrazów, zagadnień, nie mówiąc
już o potrzebie znajomości programowania (Przykłady są w Pythonie).
Być może przyda się ta książka osobom dobrze obeznanym ze sztuczną inteligencją
i matematykom.
Po prostu jest trudna i wymaga dosyć dużej wiedzy matematycznej,
dużo jest dosyć trudnych wyrazów, zagadnień, nie mówiąc
już o potrzebie znajomości programowania (Przykłady są w Pythonie).
Być może przyda się ta książka osobom dobrze obeznanym ze sztuczną inteligencją
i matematykom.
Displaying 1 - 2 of 2 reviews
Can't find what you're looking for?
Get help and learn more about the design.