Neural Networks and Learning Machines

by Simon Haykin

For graduate-level neural network courses offered in the departments of Computer Engineering, Electrical Engineering, and Computer Science. Neural Networks and Learning Machines, Third Edition is renowned for its thoroughness and readability. This well-organized and completely up-to-date text remains the most comprehensive treatment of neural networks from an engineering perspective. This is ideal for professional engineers and research scientists. Matlab codes used for the computer experiments in the text are available for download Refocused, revised and renamed to reflect the duality of neural networks and learning machines, this edition recognizes that the subject matter is richer when these topics are studied together. Ideas drawn from neural networks and machine learning are hybridized to perform improved learning tasks beyond the capability of either independently.

Genres: Computer Science, Science, Artificial Intelligence, Nonfiction, Engineering, Textbooks, Technology

936 pages, Hardcover

First published January 1, 1994

About the author

Simon Haykin was a Canadian electrical engineer noted for his pioneering work in Adaptive Signal Processing with emphasis on applications to Radar Engineering and Telecom Technology. He was a Distinguished University Professor at McMaster University in Hamilton, Ontario, Canada.

Reviews

[Ali Frz · Rating 5 out of 5]

امیدوارم پاس بشم:)
--------------
هیکین (حیکین) نویسنده فوق العاده ای است، مخصوصا این کتاب بسیار استادانه نوشته شده

[JcJet · Rating 4 out of 5]

The title of the book is very accurate: A Comprehensive Foundation. The book is big, and it gives a good understanding of how various types of ANN works, for which tasks they're best suited for.
It helped me when I was on the first year of writing my PhD thesis, to get a broader view on this field.
But as the title says, it's a good foundation. For an actual task you need to do further research on recent achievements in the architectures, and their implementation in code.

[Michael Sazonov · Rating 4 out of 5]

Сложная, масштабная, интересная книжка.

[Nandhini · Rating 2 out of 5]

Important book for my studies

[Craig Martin · Rating 4 out of 5]

I bought this book at the turn of the Millennium in Borders, Singapore, for the princely sum (back then) of S$165.99. At the time, it was the second most expensive book I had ever bought (the first was the Memoirs of Sir Stamford Raffles, purchased for A$1,000 from an antiquarian bookshop in Canberra, Australia).

I was about to graduate with distinction from INSEAD and wanted to apply my knowledge of finance to my understanding of neural networks. I had 'discovered' neural networks a decade before, in 1990, when I programmed the University of York's MIPS machine to self-organise digitized pictures of facial expressions. I wrote a Kohonen Map from scratch in C. In 2000, I had forgotten about neural networks, so I picked up Haykin's book as a refresher.

It is a book that has stood the test of time, and I dip into its pages now and then. It gives a detailed mathematical basis for the various types of machine learning. I am amazed to see the relevance of several of the models described in more recent neuroscience areas, even 25 years after the book's publication.

I gave it Four Stars.

[Tolga Durgun · Rating 4 out of 5]

It is important for my course

[Huma]

neural net