Customer Reviews

Neural Networks: A Comprehensive Foundation (2nd Edition)

5 star:		(13)
4 star:		(4)
3 star:		(2)
2 star:		(3)
1 star:		(1)

 

 

This book, excellent for self-study and for use as a textbook, covers a subject that has had enormous impact in science and technology. One can say with confidence that neural networks will increase in importance in the decades ahead, especially in the field of artificial intelligence. The book is a comprehensive overview, and does take some time to read and digest, but it is worth the effort, as there are many applications of neural networks and the author is detailed in his discussion.

In the first part of the book, the author introduces neural networks and modeling brain functions. A good overview of the modeling of neural networks and knowledge representation is given, along with a discussion of how they are used in artificial intelligence. Ideas from computational learning are introduced, as well as the important concept of the Vapnik-Chervonenkis (VC) dimension. The VC dimension is defined in this book in terms of the maximum number of training examples that a machine can learn without errors. The author shows it to be a useful parameter, and allows one to avoid the difficult problem of finding an exact formula for the growth function of a hypothesis space.

In the next part of the book, the author discusses learning machines that have a teacher. The single-layer perceptron is introduced and shown to have an error-correction learning algorithm that is convergent. There is a fine discussion of optimization techniques and Bayes classifiers in this part. The least-mean-square algorithm is generalized to the back-propagation algorithm in order to train multi-layer perceptrons along with a discussion on how to optimize its performance using heuristics. The author gives a detailed discussion of the limitations of back-propagation learning. In addition, the radial-basis function networks are introduced. Supervised learning is viewed as an ill-posed hypersurface reconstruction problem, which is then solved using regularization methods. Support vector machines are introduced as neural networks that arise from statistical learning theory considerations via the VC dimension. A summary is given of the differences between the different approaches in neural network learning machines. Committee machines, based on the divide and conquer algorithm, are also treated. Here the strategy is to divide the learning process into a number of experts, with the expectation that the collective efforts of these experts will more efficiently arrive at the solution.

The next part of the book introduces unsupervised learning machines. The ability of machines to discover useful information, such as patterns or features, in the input data is taken as an acid test for real intelligence. Hebbian learning via principal components analysis is discussed, along with competitive learning via self-organizing maps. The author uses computer simulations to illustrate the behavior of systems of neurons. Vector quantization is brought in as another supervised learning technique to fine tune the quality of the classifiers. Most interestingly, information-theoretic models are discussed with mutual information techniques used effectively as unsupervised learning algorithms. Some elementary but interesting examples of single neurons under the influence of noise are discussed in detail. The topic of Boltzmann machines is discussed also, and the physicists will find the treatment particularly fascinating, as it takes ideas from statistical mechanics and applies them to solve combinatorial optimization problems. Other more general statistical machines, such as Helmholtz machines, and mean-field theoretic approaches are discussed also. Reinforcement learning, using dynamic programming techniques is treated in detail.

The book ends with a treatment of nonlinear dynamical techniques to study the behavior of neural networks. The discussion makes use of many examples and computer experiments, and there are some good exercises at the end of the chapters for further analysis. Dynamical systems employing short-term memory and feedforward are discussed along with a treatment of stability in nonlinear dynamical systems. Feedback mechanisms are used to obtain input-output mapping. The definition of chaos is very weak, as it only employs the positivity of a Lyapunov exponent, but this is suitable for the purposes in the book.

The applications of neural networks are vast and space prevents here a comprehensive list. I have found them an excellent tool to study load balancing algorithms in distributed computing and networks, modeling of mobile communications, options pricing, and computational biology. There are also dozens of companies that specialize solely in neural network algorithms. No doubt as new learning algorithms are discovered and computers become faster, neural networks will play a major role in creating independent, autonomous, intelligent machines. This book will give the reader a solid understanding of how neural networks fit into the computational learning paradigm.

Extremely concise, extremely complete. Every new page has a new concept or method. In the first chapter, I knew more than I did after reading two other books I bought on the subject.
I would suggest, however, not to use this as an introduction. It's a bit more rigorous mathematically than some others, so use it if you understand the concepts first. It will shine new insight onto the concepts you already know, but it will probably fail at teaching them to you from the ground up.
I suggest this for the experienced Artificial Intelligence experimenter.
And for the love of god, use Perl for your test programs! Writing C++ classes for artificial intelligence is wholly impractical!

About theory, the book is good, but; it needs more practical or numerical examples, in order to get the information understandable.
There are too many concepts and ideas that without a good example, it is very hard to assimilate.
Also the computer oriented experiments in matlab, do not use the
neural network tool box, so it is not possible to get the gap to convert knowledge into computer code.
If these two recommendations are improved in a next edition, the book will become and excellent one.

thanks,

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.

I found this book to be an excellent "research" reference. It's mathematical presentation is rigorous and provides good (up-to-date)theoretical foundation for the experienced scientist/engineer. Saying this, it is not a good book for the beginner especially when one only wants to know the general physical meaning of neural networks and where it is best applied.

A wonderfully well written, insightful, treatment of artificial neural networks. Beginning from the basics, the author sets forth both a technological and historical perspective for the understanding this multidisiplinary subject area. The book is written from a practical engineering perspective and comprehensively spans the entire discipline of modern neural network theory. A+

There aren't too many words to comment on the book. If you have strong mathematical analysis basics and you love Neural Networks then you have found your book. It was hard at the beginning thus I had to brush up my memories of mathematical analysis to have the "puzzle" slowly shape up. All the algorithms are introduced by clear and rigorous mathematical theory. I think it's well suited for teachers and undergraduates.

This book is a recommended book for NN course. Many classmates regret to buy it initially as they find the book very unapproachable. I share the same view until one of my lecturers has painstakingly explained the concepts behind back-propagation and regularization. This book is one of the few where you can find the steps involved in implementing Optimal Brain Surgery. (Table 4.6). This book may discourage beginner.

This is one of the most comprehensive texts on one of the most important topics in current computer science. Though it is a graduate level text and is exorbitantly expensive, this book covers what you need to know. This book does assume a fairly sophisticated mathematical background, but those willing to bone-up on their math can understand this book quite well. If you are looking for a book to explain neural networks in detail, look no further than here.

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.