At the beginning of a calendar year that has been declared as the year of artificial intelligence (AI), with the revivals of bad and good experiences as well as fiercely debated topics in the traditional field of AI (which goes back to the Turing era and theoretical contributions), I could not find a better time to review this book.

Its appeal is also strengthened by the interplay between neural networks (who can ignore them after the success of deep learning?) and information retrieval, another long-standing and traditional subject in computer science, where searches are predominantly fuzzy and results approximate. Most promising, however, is the mention of pattern recognition as a fundamental concept for search and information retrieval.

Having read the exciting introduction of the book, with all of the above aspects used as keywords to explore further, disappointment was starting to approach as I proceeded to the following chapters.

First, the writing style and the grammatical mistakes that sneaked into the text leave the impression that high quality standards were not followed in the editing of this manuscript.

Besides, there are many repetitions with keywords such as data mining, pattern recognition, and information retrieval in each chapter, giving readers a big picture that is sometimes contradictory and misleading in terms of the book’s aim and objective.

The book’s chapters suffer from the following shortfalls:

(1) All of the chapters assume that the reader may be highly skilled in developing and applying neural networks (NNs);

(2) The topic of information retrieval falls very short, because there is no reference to current information retrieval systems or search engines where aspects of NNs can be found; hence, there is no reality check. For instance, chapter 6 discusses concurrent fuzzy neural networks without a single reference to information retrieval, as this subject is a topic on its own;

(3) Examples are missing to clarify many of the advanced mathematical concepts used throughout the book;

(4) It is very difficult to check on the validity and correctness of the mathematics and graphs from experiments discussed. Hence, advanced mathematical knowledge is recommended before reading the book;

(5) The book gives the impression that it is a collection of papers rather than a textbook that could be used for teaching at the undergraduate and postgraduate levels.

For these reasons, and the limited scope of the book, it may be best suited for PhD students who study a topic that is very close to those covered in the book.