Output details
11 - Computer Science and Informatics
Lancaster University
Article title
An uniformly stable backpropagation algorithm to train a feedforward neural network
Type
D - Journal article
Title of journal
IEEE Transactions on Neural Networks
Article number
-
Volume number
22
Issue number
3
First page of article
356
ISSN of journal
1045-9227
Year of publication
2011
Number of additional authors
2
Additional information
<12> This paper, published in high-impact IEEE Transactions (IF 2.95), introduces a new method for the online training of neural networks. The specific contribution is that the method promotes stability, the lack of which is a well-known problem of neural networks. The proposed method is applied to the problem of predicting the distribution of loads in a warehouse, but has much wider applicability and theoretical significance. Already over 1000 downloads in IEEE Explore.
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
25
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-