Stock image for illustration purposes only - book cover, edition or condition may vary.
Learning with Recurrent Neural Networks
Barbara Hammer
€ 64.55
FREE Delivery in Ireland
Description for Learning with Recurrent Neural Networks
Paperback. Folding networks, a generalization of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data. Also, the architecture, the training mechanism, and several applications in different areas are explained in this work. Series: Lecture Notes in Control and Information Sciences. Num Pages: 150 pages, biography. BIC Classification: TJFM; UYQN. Category: (P) Professional & Vocational. Dimension: 235 x 155 x 8. Weight in Grams: 530.
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 ... Read more
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 ... Read more
Product Details
Format
Paperback
Publication date
2000
Publisher
Springer London Ltd United Kingdom
Number of pages
150
Condition
New
Series
Lecture Notes in Control and Information Sciences
Number of Pages
150
Place of Publication
England, United Kingdom
ISBN
9781852333430
SKU
V9781852333430
Shipping Time
Usually ships in 15 to 20 working days
Ref
99-15
Reviews for Learning with Recurrent Neural Networks