loading 
register   login

Neural Networks: A Comprehensive Foundation (2nd Edition)

by: Simon Haykin
en

9780132733502  0132733501 

Neural Networks: A Comprehensive Foundation (2nd Edition)
By Simon Haykin




Product Description:

Pres a comprehensive foundation of neural networks, recognizing the multidisciplinary nature of the subject, supported with examples, computer-oriented experiments, end of chapter problems, and a bibliography. DLC: Neural networks (Computer science).




Summary: Neural networks in statistical framework
Rating: 5

Haykin is pretty well established in his area and he definitely produces high quality work. the book is quite complete. What I particularly like about this book is that it connects neural networks to other machine learning techniques, such as support vector machines, Boltzmann machines, independent component analysis etc. Another plus of this book is the presentation of algorithms. Haykin gives very detailed description of the algorithms presented. Even if you might not want to understand all the mathematical details you will be able to implement them.



Summary: Good info, heavy on the math, but too preachy and not for the faint of heart.
Rating: 4

An excellent entry level text on the subject. The author covers most aspects of neural networks, although not quite as in depth as I had hoped in some areas. Suitable for use as a textbook if you are taking a class on the subject, or as a self study book. Gets a bit too preachy and defensive about the practicality of neural networks. The author obviously cut his teeth in NN's during the 60/70's. IMO anyone who already bought the book doesnt need convincing that neural networks work. I recommend at least a working knowledge of calculus and statistical analysis.



Summary: A good book with a very mathematical viewpoint
Rating: 4

If you are going to start learning neural networks, this is probably the best book with which to begin. It does a good job in how it progresses through the subject. It spends two chapters introducing the subject in a very complete fashion, then five chapters more on the subject of supervised learning with neural networks, and five more chapters on unsupervised learning. The final three chapters gets off into the subject of non-linear dynamical systems.

Although the book is very complete, it is also mathematically rigorous. To really understand it from cover to cover you would need to know - both conceptually and practically - calculus, linear algebra, adaptive signal processing, and dynamical systems, since this book assumes you already know these subjects and makes heavy use of their properties. Fortunately, to get a good basic understanding of what neural networks are and what they can accomplish, you won't need to understand the entire book. I found chapters 1-7 to be fairly accessible and self-contained. It is only once you get past the subject of supervised learning in chapter eight that the mathematics and the book get particularly difficult. Another problem with the book is that it abruptly goes from a forest to a trees viewpoint of neural networks. It will be working along in a very theoretical manner for some number of pages, when suddenly, out of nowhere, it will mention something practical or show an example that clarifies a great deal. Therefore you will need to read the book carefully.

My personal recommendation is that you go through the first seven chapters of this book to get a good viewpoint of the theoretical basics of neural networks and supervised learning, and then read Jeff Heaton's "Introduction to Neural Networks with Java" to get a good practical viewpoint on the subject. Then, if you need to return to the book for the more advanced chapters, you will be better prepared. It would also be best to use this book in conjunction with taking a course on the subject. I think it would be very rough going to try to understand this book via self-study alone.



Summary: Neural Networks Foundations
Rating: 5

This is the first book for everyone interested in the subject. A well-written and well-illutrated encyclopedia of Neural projects, including all the fundamental questions at the forefront of research in Neural Networks. I believe this is the reason for it beeing widely referenced by almost all the authors in the subject.



Summary: Very Mathematical
Rating: 3

I used this as a textbook for a Neural Networks course I did in the second year of my undergraduate program in Mathematics and Computing.

My mathematical background till that point of time comprised Linear Algebra and upper level Calculus. This being rather 'limited' mathematical exposure, I found the book quite difficult to follow. It becomes harder when you are expected to convert the mathematical equations into working programs (without using tool-boxes or libraries, i.e.). The end-of-chapter exercises are pretty hard, and try to go beyond what the text talks about, most undergraduates may not be able be able to appreciate that. I think this is an excellent reference book for those who are pretty comfortable with Math. For undergraduates doing a first course in Neural Networks, I strongly recommend Timothy Masters' "Practical Neural Network recipes in C++". The math there is manageable, and yes, it comes with working code to make your life easier.