To say this book is confusing is an understatement. I am a veteran C++ programmer, with a background in financial application development, looking to expand my skill set. I found this book to be a waste of money.
The chapter on object oriented (OO) programming should have been a warning to me. I remember reading it and thinking, "It's a good thing I'm already familiar with OO, because I would never be able to figure it out from this chapter". I'm not terribly familiar with Neural Networks or Fuzzy Logic and, after reading the first four chapters, I am even more confused than when I started. I think that each topic is getting the same poor treatment that the OO chapter received.
The explanations in this book are useless. Here is an excerpt about how to figure out how many patterns a four node Hopfield network may recall (by the way, the reader is never told what a Hopfield Network is, but is left to infer the key characteristics of a Hopfield Network by comparing the given example to a previous example - which was apparently not a Hopfield network).
"If a pattern P has k, less than 4, bit positions with 0 (and so 4-k bit positions with 1), and if pattern Q is to be orthogonal to P, then Q can have 0 or 1 in those k positions, but it must have only 0 in the rest 4-k positions. Since there are two choices for each of the k positions, there are 2[to the kth power] possible patterns orthogonal to P. this number 2[to the kth power] of patterns includes the pattern with all zeroes. So there really are 2[to the kth power]-1 non-zero patterns orthogonal to P. Some of these 2[to the kth power]-1 patterns are not orthogonal to each other. As an example, P can be the pattern 0 1 0 0, which has k = 3 positions with 0. There are 2[to the 3rd power]-1=7 non-zero patterns orthogonal to 0 1 0 0. Among these are patterns 1 0 1 0 and 1 0 0 1, which are not orthogonal to each other, since their dot product is 1 and not 0." Pg 64
Surely there is a better, and more understandable, way to explain this concept (and every other concept in this book).
I get the feeling that the authors are just going through the motions. They must have created an outline of topics that should be included in a book entitled C++ Neural Networks & Fuzzy Logic but spent little time populating each topic with meaningful information. There seems to be just enough information under each heading to enable someone who already knows the subject to say, "yes that is correct".
This book is a mess.