Artificial intelligence has been widely hyped for its potential to transform a broad swath of industries, from cybersecurity to medicine. Now, we might start to get a clearer picture for how it could be used to change the way we shop. Macy's announced Wednesday that it has teamed up with IBM Watson to use artificial intelligence as a customer service tool in 10 of its stores. The retailer dubbed the pilot program "Macy's On Call," and it will allow customers to type in questions on their phones and receive answers. Unlike some chatbots that can only regurgitate preprogrammed responses based on keywords, IBM Watson will learn over time to give better answers that are customized to individual stores.

This fall, customers cruising the aisles of Lowe's home improvement stores in the San Francisco Bay Area may see a new type of employee taking inventory and assisting shoppers. You won't find a nametag on this worker, but you won't confuse it with other employees, either. The new kid in town is the LoweBot, an autonomous retail service robot that scans and audits store inventory on the floor. It uses voice recognition to identify products for customers and lead them to the right shelf -- in multiple languages. The retailer is deploying LoweBots at 11 of its Bay Area stores over a seven-month period using NAVii robots made by Fellow Robots, following a successful two-year pilot program of a first-generation robot called OSHbot that was tested at one of Lowe's Orchard Supply Hardware stores.

The author has performed an excellent job in explaining the fundamental ideas and practical methods of different AI techniques. AI problems in the field ( pattern recognition, speech and image processing, classification, planning, optimization, control, time-series and analogy-based prediction, diagnosis, decision making and game simulations) are discussed and illustrated with examples . Especially useful are the comparisons between different techniques (AI rule Cbased methods, fuzzy methods, connectionist methods, and hybrid systems for knowledge engineering) used to solve the same or similar problems. The presented text is suitable for advanced undergraduate and postgraduate students as well as a reference for researchers in the field of knowledge engineering.The book¡ s appendices summarize data sets for the examples in the book. All data sets are available through anonymous FTP.

The Master Algorithm is a book about Machine Learning. But while it claims to be about its future, the focus is more on its past. Domingos' gives us a tour of the five different Machine Learning fiefdoms (Evolutionaries, Connectionists, Symbolists, Bayesians, and Analogizers), how they connect, and what their histories are. At times the discussion gets a little too technical. Sentences like "...we can view what SVMs do with kernels, support vectors, and weights as mapping the data to a higher-dimensional space and finding a maximum-margin hyperplane in that space" (pg 196) make it clear Mr. Domingos is no Malcolm Gladwell.

While I still need to examine this area in more depth, this book seems to have the key elements needed to start working. The fact that it is using Perl and Prolog is not a big deal since the key points of the code examples are sufficiently explained to port it to whatever language you might want to use.

This book is a delight for anyone who deals with practical Data Mining applications. Over the past few years, I have gathered bits and pieces of knowledge from various sources about machine learning, Map Reduce programming paradigm, design and analysis of algorithms, information retrieval, etc. But this book serves to tie it all together beautifully. If you have delved in the above topics and are looking for a reference book that strikes a balance between rigor and practicality, this book will serve you right. On the other hand, if you are just starting out in the field of Data Mining/Machine Learning then you may do well by starting out with more detailed material.

This book claims to be an overview of artificial intelligence, but it's not; it's an overview of machine learning. It's true that machine learning is a hot topic within AI just now, but it's hardly taken over the field, nor has it rendered all other methods obsolete. But, if you just want an informal introduction to the basic forms of machine learning, it's short and easy to read. The rubber never quite meets the road, but if all you need is the basic concepts, it's not a bad start. It does, however, contain errors that really should have been caught prior to publication. In addition to the errors mentioned by another reviewer, the references to equations 10.2 through 10.4 are wrong, and the description of the logistic function shown in Figure 10.3 doesn't match the function shown.

Starts from fundamentals, and builds up. Just in case you don't have a background in signal processing and z-transforms, the author takes two semesters of electrical engineering and compresses them into chapter 10. Goes on to cover acoustics, MFCC, PSOLA, HMMs, unit selection, prosody and intonation, system architectures, etc. This is a solid graduate-level or advanced undergraduate textbook. It gives a comprehensive, in-depth overview coverage of the state of the art in TTS best practices as of 2009.

I purchased the book in order to learn a bit more on big data and machine learning. This is a nicely written book with all of the fundamental concepts in big data and machine learning. With every concept clearly explained with examples and graphs, accompanied with R codes. An example is the Patterns of Big data in Section 3.3, where the author explained different pattern evolutions are to be used for supervised learning. As the selected features increase, class separation by the standardization is then clearly demonstrated to be an efficient and accurate method.

I used this book as a textbook for a special topics course on computational biomedicine that I taught twice so far at a graduate level. The book offered the foundational knowledge level for the course. The CI part is basic and needs good support, and that was not a problem, given that I cater to an engineering audience. No matter how good a book is for a graduate course, you would still need to offer support through readings from recent journal and conference publications. Yet, this book was good enough to put students on track for doing basic experiments using some of its researched ideas and works. Recently, I tried to find a substitute for this book, mainly because my institution requires using recently published books that are no more than 6 years old, and also because I needed an update on the material.