Neural Networks: A Comprehensive Foundation (2nd Edition)

Rating:
Summary: Informative and masterfully written.
Review: 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+

Rating:
Summary: Not that good
Review: Considering all the other clearly written and mathematically complete books on neural network theory you should not waste your time with this one. For feedforward nets try bishop's book, which, though mathematically more difficult, gives real insight into the complex behavior of these types of nets. Rock on.

Rating:
Summary: Not that good
Review: Considering all the other clearly written and mathematically complete books on neural network theory you should not waste your time with this one. For feedforward nets try bishop's book, which, though mathematically more difficult, gives real insight into the complex behavior of these types of nets. Rock on.

Rating:
Summary: I wish all books were like this.
Review: 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!

Rating:
Summary: Well written and fairly comprehensive
Review: Haykin's book is probably the most comprehensive compendium of traditional neural network theory currently available. I say "traditional" because historically neural networks developed within the field of computer science, only loosely inspired by actual neuroscience. Feedforward networks, backpropagation, self-organizing maps, PCA, and hierarchical machines fit into this traditional lineage. A second branch of neural networks, inspired more heavily by biology, have sought to model brain function and structure. Within this camp are network models such as adaptive resonance theory (ART), BCS/FCS, integrate-and-fire models, and a variety of others. Though this second branch of neural network theory has applications in pattern recognition, image processing, clustering, etc., Haykin barely mentions it. In other words, Haykin presents the material that computer scientists and engineers want to see, but skimps on the more biological side of the field. That being said, the material covered in Haykin is very well-presented, with clear mathematical notion and typesetting throughout. The book is accessible to graduates and advanced undergraduates. It should be on the shelf of every serious researcher, though workers in the biological sciences may want supplementary material. Computer scientists, mathematicians, and other engineers will not be disappointed at all.

Rating:
Summary: Well written and fairly comprehensive
Review: Haykin's book is probably the most comprehensive compendium of traditional neural network theory currently available. I say "traditional" because historically neural networks developed within the field of computer science, only loosely inspired by actual neuroscience. Feedforward networks, backpropagation, self-organizing maps, PCA, and hierarchical machines fit into this traditional lineage. A second branch of neural networks, inspired more heavily by biology, have sought to model brain function and structure. Within this camp are network models such as adaptive resonance theory (ART), BCS/FCS, integrate-and-fire models, and a variety of others. Though this second branch of neural network theory has applications in pattern recognition, image processing, clustering, etc., Haykin barely mentions it. In other words, Haykin presents the material that computer scientists and engineers want to see, but skimps on the more biological side of the field. That being said, the material covered in Haykin is very well-presented, with clear mathematical notion and typesetting throughout. The book is accessible to graduates and advanced undergraduates. It should be on the shelf of every serious researcher, though workers in the biological sciences may want supplementary material. Computer scientists, mathematicians, and other engineers will not be disappointed at all.

Rating:
Summary: Well written and fairly comprehensive
Review: Haykin's book is probably the most comprehensive compendium of traditional neural network theory currently available. I say "traditional" because historically neural networks developed within the field of computer science, only loosely inspired by actual neuroscience. Feedforward networks, backpropagation, self-organizing maps, PCA, and hierarchical machines fit into this traditional lineage. A second branch of neural networks, inspired more heavily by biology, have sought to model brain function and structure. Within this camp are network models such as adaptive resonance theory (ART), BCS/FCS, integrate-and-fire models, and a variety of others. Though this second branch of neural network theory has applications in pattern recognition, image processing, clustering, etc., Haykin barely mentions it. In other words, Haykin presents the material that computer scientists and engineers want to see, but skimps on the more biological side of the field. That being said, the material covered in Haykin is very well-presented, with clear mathematical notion and typesetting throughout. The book is accessible to graduates and advanced undergraduates. It should be on the shelf of every serious researcher, though workers in the biological sciences may want supplementary material. Computer scientists, mathematicians, and other engineers will not be disappointed at all.

Rating:
Summary: Theoretically Great
Review: 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.

Rating:
Summary: Hard to digest if you are not an engineer
Review: I imagine this is a great book if you have a background in engineering. I took an engineering course with this book as the course text. Because I did not have the background, I struggled with the text and the problem sets.

Rating:
Summary: A Comprehensive Book
Review: I Like this book...it even has PCA analysis theeory in it...very nice, practical and sound.