Neural Networks for Pattern Recognition | 
 enlarge | Author: Christopher M. Bishop
Publisher: Oxford University Press, USA
Category: Book
List Price: $105.00
Buy New: $61.47
You Save: $43.53 (41%)
New (25) Used (11) from $44.99
Avg. Customer Rating:  20 reviews
Sales Rank: 177031
Media: Paperback
Edition: 1
Number Of Items: 1
Pages: 504
Shipping Weight (lbs): 1.7
Dimensions (in): 9 x 6.1 x 1.1
ISBN: 0198538642
Dewey Decimal Number: 006.4
EAN: 9780198538646
ASIN: 0198538642
Publication Date: January 18, 1996
Availability: Usually ships in 1-2 business days
Shipping: International shipping available
Condition: Brand new book delivered from the UK in 10-14 days.
|
| Also Available In:
|
| Similar Items:
|
| Editorial Reviews:
Amazon.com Review
This book provides a solid statistical foundation for neural networks from a pattern recognition perspective. The focus is on the types of neural nets that are most widely used in practical applications, such as the multi-layer perceptron and radial basis function networks. Rather than trying to cover many different types of neural networks, Bishop thoroughly covers topics such as density estimation, error functions, parameter optimization algorithms, data pre-processing, and Bayesian methods. All topics are organized well and all mathematical foundations are explained before being applied to neural networks. The text is suitable for a graduate or advanced undergraduate level course on neural networks or for practitioners interested in applying neural networks to real-world problems. The reader is assumed to have the level of math knowledge necessary for an undergraduate science degree.
Product Description
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition. After introducing the basic concepts, the book examines techniques for modelling probability density functions and the properties and merits of the multi-layer perceptron and radial basis function network models. Also covered are various forms of error functions, principal algorithms for error function minimalization, learning and generalization in neural networks, and Bayesian techniques and their applications. Designed as a text, with over 100 exercises, this fully up-to-date work will benefit anyone involved in the fields of neural computation and pattern recognition.
|
| Customer Reviews: Read 15 more reviews...
 Only for an expert July 20, 2006
6 out of 6 found this review helpful
Mr Bishop's book is very well written and contains a lot of useful information on neural networks. It is outlined well and progresses in a logical form. If, however, you are looking for a book that gives discussions with concrete examples of neural networks applications or set ups, you will be sorely disappointed. The mathematical treatment is universally generalized with very few specific concrete examples shown. Even the exercises will not serve you well. The term 'graded' is used; however, that simply referes to the description of difficulty. There are no answers to these exercises, so unless you have a teacher or are already firmly familiar with the material, you will not know if you have completed them correctly or not. Even worse, the exercises are in general not written to reinforce concepts in the chapter, but in most cases extend the chapter material into new regions.
In summary, this book should only be purchased by someone already familiar with neural networks and their mathematical basis. Anyone else will be wasting their money.
Fabulous April 6, 2006
2 out of 2 found this review helpful
This is the best book I have found for a general study of the of neural networks. I found this particularly useful when looking at how to write my own NN frameworks. The depth of the mathematics allowed me to easily answer questions like: 'what if I replaced function abc with xyz'. I have found other texts failed to show key mathematical derivations, or to explore the subtleties of what the maths imply.
The book covers a plethora of topics from simple gradient descent through second order techniques and conjugate gradient, through to the use of 'bayesian techniques' (basically confidence intervals on network outputs), monte carlo techniques etc. Similarly error functions, non-linearities (sigmoids, softmax etc.) and data preparation are all treated.
The extensive bibliography also provides excellent references for further study, (a whos who of the field, as well as actual titles). My copy is now dog earred from frequent reading.
Sheer pleasure. January 28, 2004
4 out of 6 found this review helpful
If you want a very good, intermediate introduction to pattern classification this book must be on your bookshelf. It even does a very nice job explaining the EM algorithm in a few pages! Basic calculus is all you need to understand the book. A must read.
It makes a difficult topic easy to understand September 15, 2003
3 out of 5 found this review helpful
The theories of NN and PR are quite difficult to understand. But this book makes them much easier. The author can explain the concepts without using too much formula. If other authors could follow his step then the life is much easier!
Recomended book to read July 22, 2003
0 out of 1 found this review helpful
This is a recommended book to read for people who would like to read about statistics and maths. People with few knowledge about these sciences will find it a bit difficult to read.
|
|
|
