|
|
books
| book details |
Learning with Recurrent Neural Networks
By (author) Barbara Hammer
|
| on special |
normal price: R 2 114.95
Price: R 1 903.95
|
| book description |
Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively.
| product details |
Normally shipped |
Publisher | Springer London Ltd
Published date | 30 May 2000
Language |
Format | Paperback / softback
Pages | 150
Dimensions | 235 x 155 x 0mm (L x W x H)
Weight | 0g
ISBN | 978-1-8523-3343-0
Readership Age |
BISAC | computers / neural networks
| other options |
|
|
To view the items in your trolley please sign in.
| sign in |
|
|
|
| specials |
|
|
|
Mason Coile
Paperback / softback
224 pages
was: R 520.95
now: R 468.95
|
A terrifying locked-room mystery set in a remote outpost on Mars.
|
An epic love story with the pulse of a thriller that asks: what would you risk for a second chance at first love?
|
|
|
|
|
