Rating: 
Summary: A real bad one
Review: This is the wrong book for any student or practioner of neural nets. It does not go into the theory of neural networks enough, though it does explain back-propagation methods (superficially though) it doesn't even provide any helpful codes beyond the very rudimentry, so whether you are looking for a sold foundation on NNs or a quick fix (read code), this book provides neither. For a solid foundation, I would recommend Simon Haykin's book.
Rating:
Summary: A real bad one
Review: This is the wrong book for any student or practioner of neural nets. It does not go into the theory of neural networks enough, though it does explain back-propagation methods (superficially though) it doesn't even provide any helpful codes beyond the very rudimentry, so whether you are looking for a sold foundation on NNs or a quick fix (read code), this book provides neither. For a solid foundation, I would recommend Simon Haykin's book.
Rating:
Summary: Don't buy this book.
Review: Very nice job. The only negative criticisms I have deal with the computer code: 1) The appendix does not do a good job of describing how to run the code. The various input parameters are described, but that's about it. Not even a short description on how to compile the code. 2) The author claims the C++ code is ANSI standard. This is not true. The code as distributed requires the "conio" library, which is not an ANSI standard! However, for others who come across this, simply comment out all references to "kbhit()", "getch()", and create an empty file "conio.h" and you should be in business.
Rating: 
Summary: Very comprehensive, well written. Code needs better doc.
Review: Very nice job. The only negative criticisms I have deal with the computer code: 1) The appendix does not do a good job of describing how to run the code. The various input parameters are described, but that's about it. Not even a short description on how to compile the code. 2) The author claims the C++ code is ANSI standard. This is not true. The code as distributed requires the "conio" library, which is not an ANSI standard! However, for others who come across this, simply comment out all references to "kbhit()", "getch()", and create an empty file "conio.h" and you should be in business.
Rating: 
Summary: Great intro to neural networks -- Many examples
Review: When I received Pratical Neural Network Recipes in C++, I was pleasantly surprised on how easy it was to follow. Even though I have an extensive calculus background, I believe almost anyone with a background in statistics or college algebra can follow along. As far as content, Masters has shown his ability to explain a complex subject without making it overly complex. I was happy that Masters did not get too in depth with mathmatical proofs. Instead, he sticks to the point -- how to make artificial neural networks that aid in everything from pattern recognition to stock forecasting. He also explains several different kinds of networks such as genetic, hybrid, and multilayer feedforward, and the various benefits and pitfalls of each. The Neural program that comes with the book was also of great help (It's on a 3 1/2 floppy, not a 5 1/4). I recommend this book to anyone who wants to learn about NN's.
| 
