
Learning with Recurrent Neural Networks - Lecture Notes in Control and Information Sciences 254 (Paperback)
Barbara Hammer (author)
£89.99
Paperback
150 Pages
Published: 30/05/2000
Published: 30/05/2000
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.
Publisher: Springer London Ltd
ISBN: 9781852333430
Number of pages: 150
Weight: 530 g
Dimensions: 235 x 155 x 8 mm
Edition: 2000 ed.
You may also be interested in...
Please sign in to write a review
Sign In / Register
Not registered? CREATE AN ACCOUNTCREATE A plus ACCOUNT
Sign In
Download the Waterstones App
Would you like to proceed to the App store to download the Waterstones App?
Click & Collect
Reserve online, pay on collection
Thank you for your reservation
Your order is now being processed and we have sent a confirmation email to you at
When will my order be ready to collect?
Following the initial email, you will be contacted by the shop to confirm that your item is available for collection.
Call us on or send us an email at
Unfortunately there has been a problem with your order
Please try again or alternatively you can contact your chosen shop on or send us an email at