Rating: 
Summary: How to build 'em - How to use 'em - And actual source code!
Review: Easily the best treatment of neural networks I have ever read. Outstanding treatment of the innards, how they work, and years of practical experience boiled down into heuristics for programming (with optimized source code examples!), configuring, training, and evaluating nets. The theory is brilliantly explained within each topical context in lieu of boring chapters on NN theory and math. Mathematical expressions are used only where they add clarity and are not gratuitiously used where the author's excellent English can do the job. And talk about English! Masters is one of those phenoms who speak math and English with equal facility. The writing is simply outstanding. The book is so good it is hard to decide what parts are most valuable. Amazingly, it is as useful for the novice wanting to learn something about neural nets as it is for a professional looking for tips and techniques! I have made the book mandatory reading for my team of knowledge discovery scientists and engineers
Rating: 
Summary: The wrong book to get for NN study!
Review: I do not recommend this book. I returned it within 10 days of my purchase, as I found it hard to follow and vague in many areas. Instead of buying this book, I recommend Object Oriented Neural Networks in C++ by Joey Rogers. It provides a very clear explanation of what NNs are, how they work, and how to implement them.
Rating: 
Summary: Good practical book on NN's
Review: I found this book a very good introduction to NN's. In particular it does a good job of describing the foundations and pitfalls of NN's. I believe that the author probably has more of a practical grounding in NN's than most given his experience in the defence industry. I also have Rogers' book, Looney (Pattern Recognition Using NN's) and Masters second book. Sure the code in this is not OO but it is probably the most readable C you will ever get in a book, easy to compile and I didn't find many errors in the compilation (Borland CBuilder, GCC) however I did keep getting errors in Rogers' code (not declaring variables (CBuilder) ). If you can understand C you can read the code and understand NN's. The description of annealing is better than most geostatistical texts.As mentioned by others, running the programs takes a bit of working out and this is the main defficiency I find. Looney's and Rogers' books are more academic and I find slightly harder to follow. Rogers' introduces a description language for NN's which I didn't find useful. I find it easier to read the code and each chapter and that has given me a reasonable understanding of NN's. Looney and Rogers' cover different algorithms. Rogers' OO approach is good. I have used Looneys RBFLN and it works well for my applications. My interest in NN's is practical applications in the earth sciences and my reading/interest is based around this. I am a med level C/C++ programmer who writes command line hacks to do data work and use OO when I have the time to clean up code. The title of this book really sums up what it is all about (as do Carl Looney's and Joey Rogers' Titles !!)
Rating:
Summary: Supurb practical text
Review: I'll keep it brief. I've bought this book already a long time ago. And now and then still delve into it. Like many have said bfore me,it's exactly what the title says it is. A practical intro with plenty of readable source.If people think the theory side is a bit light,they're ofcourse right, but that is exactly what the author intended to do.This book delivers on what it promises,no more no less.You can actually get to work after reading it ;)
I would for instance recommend "Bishop, Neural networks for pattern recognition" to get a more solid foundation,(which admittedly is not a bad idea). All in all worth every penny/dollar/euro.
Rating:
Summary: This book is a big lie
Review: On a scale of 1 to 5, I wanted to rate this book as zero. On page 423, this book says "Complete code can be found on the accompanying disk." This is a big lie. The author only gives partial listing in the accompanying disk, which completely makes you beserk. You can never understanding this book, when the codes are given incomplete. He is like giving a final exam to his students, where he is requiring his students to complete his codes. It may be OK if he hides some of his codes, but he should not lie. It is this advertisement that he is providing the complete code that induced me to buy his book.
Since he is holding some of the codes, the source codes provided in the disk will never build.
Rating:
Summary: A good start
Review: Some of the other reviewers of this book must have suffered from a misconception about the book. It is exactly as advertised, if you don't think so, compare it to Neural Networks, A Comprehensive Foundation by Haykin or Artificial Neural Networks by Schalkoff. Those are REALLY academic. Neural Networks is a very difficult topic,but this book does the best job I've seen yet of explaining Neural Nets in a Straightfoward, understandable way. C++ Neural Networks & Fuzzy Logic by V. and H. Rao tried this and failed. The math is very needed, and I respect the approach of only looking at one type of neural net (feedfoward 3 layer) in depth rather than a billion short, unexplained looks a many. Yes, the code is not the best I've ever seen, and it gets a bit rough to follow, but it explains the ideas. Overall I'd say know a little about what you're getting into before buying ANY book on Neural Networks.
Rating:
Summary: Fantasic introduction to neural networks.
Review: The author does a great job with this book. He presents the complex material of neural networks in a very simple manner making it understandable to anyone interested in: (1) finding out more about neural networks, (2) using neural networks in any field, (3) applying neural networks in any field of research (ie: medicine, biology, finance, etc...). The author goes over everything that one needs to know about neural networks -- from the basics to how to implement your own network. Not only does he present the material in a concise manner, but he also gives C++ code to implement a neural network both in the book and on disk. Overall, I think that this is an excellent book to begin with if you are interested in neural networks and their applications.
Rating:
Summary: Don't buy this book.
Review: The book's title is misleading. They should have take out the words "Practical" and "C++". It's very academic, and a few REAL C++ codes. This book is not for beginners, and not practical, not written with C++ in mind (or OO programming). The first impression I've got when I opened this book is that I thought I was reading someone's thesis.
Rating:
Summary: Very practical indeed
Review: This book is exactly as advertised. Other excellent books on Neural Networks will have you buried in mathematical notation that will challenge even readers with some statistics background and a couple of semesters of Calculus. These books are definitely worth your while if you can handle the math, but even then, translating these books from theories to solving real problems is no easy feat. By contrast, this book presents a good introduction to basic feedforward neural networks that is very readable to users with a moderate math background, and probably readable with some effort for motivated readers with limited math. You can read this book and come away with a reasonable understanding of how a feedforward network functions. Still, that's not even the strength of this book. Not only is this book "practical" in the sense that it is readable, it is practical in that it tackles a host of additional topics necessary for using a neural network in the real world. It discusses annealing and genetic techniques for avoiding local minima. It discusses singular value decomposition for avoiding problems with redundant inputs. It discusses the best ways of building training sets and preparing input data, as well as ways of evaluating the performance of networks and attaching confidence measures. It would be easy to charge right in, use a neural network as a black box, give it a dataset and train it, and then wait for it to pop answers out. The only problem is, this will yield results that are worthless in the real world. All of these concerns have to be addressed to build a model that can actually be used for something. I was very happy with the code base included with this book as well. In addition to a neural network using conjugate gradient descent (as well as Kohonen learning), code is integrated into the main program for annealing, genetic initialization, and singular value decomposition, as discussed in the text. I found the section on how to use the program slightly confusing at first, but once I figured out how to operate it, it was easy to set it up and use it. The code base is C++ that is deeply rooted in C, so it won't impress object-oriented gurus at all, but it should be understandable and fairly easy to work with for users with a good background in C, but who aren't C++ experts. For me, the bottom line is that the code works, it's not hard to understand (in my opinion), and it shouldn't be that hard to extend to perform new functions. In this day and age, it's probably worth mentioning that the program comes with a simple command-line interface, so if you want something that runs in a spiffy GUI, you'll have to write one. I would recommend this book strongly as a first book on neural networks for readers that are interested in learning neural networks in the context of solving practical problems. I would also recommend this book to readers who have a book or two discussing the theoretical aspects of neural networks and want something that will help them translate that into attacking practical problems, and also provide a code base that will give them a head start.
Rating:
Summary: Complete C++ Source Code for Many Common Neural Network Algo
Review: This book is exactly what is described by its title. It presents a cookbook of neural network recipes for the C++ programmer. I have used this book often, as I have developed a number of C++ and Java based Neural Network applications. The books is readable(at least as far as AI books go), it does not read like a mathematics text book, as many other AI books do. The chapters are logically broken into the major neural network tasks: classification (identifying something), autoassociation (identifying a pattern by returning the same pattern), Time-Series Prediction (this is commonly applied to predicting the stock market, etc), Function Approximation. As the author introduces these topics, various network architectures are discussed, such as feed-forward, multi-layer, backpropagation, and probalistic networks. Network optimization methods such as eluding local minima are tackled through the use of genetic algorism and simulated annealing.
|
