An explanation of how the high-speed capabilities and "learning" abilities of neural networks can be applied to solving numerous complex optimization problems in electromagnetics. It seeks to help the reader understand the basics and strengths and limitations of each main network architecture in use today. Moreover, it identifies situations when the use of neural networks is the best problem-solving option.
FREE Two-Day Shipping for students on millions of items. Learn more |
| ||||||||||||
Book Description
Product Details
Would you like to update product info or give feedback on images?
|
More About the Author
Discover books, learn about writers, read author blogs, and more.
Customer Reviews
|
There are no customer reviews yet.
|
|||
|
Video reviews
|
Inside This Book
(learn more)
First Sentence:
As discussed in Chapter 1, the layered feed-forward NNs (commonly referred to as perceptrons) are amongst the most popular NN architectures. Read the first page Key Phrases - Statistically Improbable Phrases (SIPs): (learn more)
node jmax, first list presentation, uncommitted node, synchronous transition mode, vigilance criterion, cascaded gratings, update gradient descent, array output vector, committed nodes, binary representation scheme, sequence input pattern, various geometric parameters, vigilance parameter, function approximation problem, interconnection weights, desired frequency response, gradient descent procedure, perceptron learning rule, harmonic balance technique, sigmoidal type, perceptron learning algorithm, nodal voltages, sum scheme, bias node, training list Key Phrases - Capitalized Phrases (CAPs): (learn more)
Neural Computation, Elsevier Science, New York, Applied Optics, Optical Society of America, Artech House, Connection Science, International Conference, Order of Search, Effect of the Choice Parameter, Vehicular Technology, Finding Structure, Cognitive Science Society Inc, User's Guide, Fast Learning, Comprehensive Foundation, Information Theory, Perseus Book Publishers, Perseus Books, Prentice Hall, Boston University, Fifth Edition, Hertz Figure, Iteration Index Figure, John Wiley New!
Books on Related Topics | Concordance | Text Stats Browse Sample Pages:
Front Cover | Table of Contents | First Pages | Index | Back Cover | Surprise Me!
As discussed in Chapter 1, the layered feed-forward NNs (commonly referred to as perceptrons) are amongst the most popular NN architectures. Read the first page Key Phrases - Statistically Improbable Phrases (SIPs): (learn more)
node jmax, first list presentation, uncommitted node, synchronous transition mode, vigilance criterion, cascaded gratings, update gradient descent, array output vector, committed nodes, binary representation scheme, sequence input pattern, various geometric parameters, vigilance parameter, function approximation problem, interconnection weights, desired frequency response, gradient descent procedure, perceptron learning rule, harmonic balance technique, sigmoidal type, perceptron learning algorithm, nodal voltages, sum scheme, bias node, training list Key Phrases - Capitalized Phrases (CAPs): (learn more)
Neural Computation, Elsevier Science, New York, Applied Optics, Optical Society of America, Artech House, Connection Science, International Conference, Order of Search, Effect of the Choice Parameter, Vehicular Technology, Finding Structure, Cognitive Science Society Inc, User's Guide, Fast Learning, Comprehensive Foundation, Information Theory, Perseus Book Publishers, Perseus Books, Prentice Hall, Boston University, Fifth Edition, Hertz Figure, Iteration Index Figure, John Wiley New!
Books on Related Topics | Concordance | Text Stats Browse Sample Pages:
Front Cover | Table of Contents | First Pages | Index | Back Cover | Surprise Me!
Citations (learn more)
This book cites 34
books:
See all 34 books this book cites
14
books
cite this book:
See all 14 books citing this book
- Neural Networks: A Comprehensive Foundation (2nd Edition) by Simon Haykin on 5 pages
- Introduction To The Theory Of Neural Computation, Volume I (Santa Fe Institute Series) by John A. Hertz on 4 pages
- Pattern Recognition Principles by Julius T. Tou on 4 pages
- Introduction to Adaptive Arrays by Robert A. Monzingo on page 360, and page 427
- Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations (Volume 1) by David E. Rumelhart in Front Matter, and page 117
See all 34 books this book cites
- Electromagnetic Modeling of Composite Metallic and Dielectric Structures by Branko Kolundzija in Back Matter
- Analytical Modeling in Applied Electromagnetics (Artech House Electromagnetic Analysis Series) by Sergei Tretyakov in Back Matter
- Wavelet Applications in Engineering Electro- magnetics by Tapan K. Sarkar in Back Matter
- Adaptive Array Measurements in Communications (Artech House Antennas and Propagation Library) by M. A. Halim in Back Matter
- Computational Electrodynamics: The Finite-Difference Time-Domain Method (Artech House Antennas and Propagation Library) by Susan C. Hagness in Back Matter
See all 14 books citing this book
Books on Related Topics
(learn more)
|
Tag this product(What's this?)Think of a tag as a keyword or label you consider is strongly related to this product.
Tags will help all customers organize and find favorite items. |
Sell a Digital Version of This Book in the Kindle Store
If you are a publisher or author and hold the digital rights to a book, you can sell a digital version of it in our Kindle Store.
Learn more
Customer Discussions
|
This product's forum
Active discussions in related forums
Search Customer Discussions
|
Related forums
|
Listmania!
So You'd Like to...
Look for Similar Items by Category
- Books > Computers & Technology > Certification
- Books > Computers & Technology > Computer Science > Artificial Intelligence > Neural Networks
- Books > Computers & Technology > Programming > Algorithms
- Books > New & Used Textbooks > Computer Science
- Books > New & Used Textbooks > Science & Mathematics
- Books > Professional & Technical > Engineering
- Books > Science & Math > Physics > Electromagnetism
