EPSRC Reference: |
GR/L19232/01 |
Title: |
ANALYSIS OF ON-LINE LEARNING IN NEURAL NETWORKS |
Principal Investigator: |
Saad, Professor D |
Other Investigators: |
|
Researcher Co-Investigators: |
|
Project Partners: |
|
Department: |
Electronic Engineering |
Organisation: |
Aston University |
Scheme: |
Standard Research (Pre-FEC) |
Starts: |
01 November 1996 |
Ends: |
31 March 1999 |
Value (£): |
106,235
|
EPSRC Research Topic Classifications: |
|
EPSRC Industrial Sector Classifications: |
|
Related Grants: |
|
Panel History: |
|
Summary on Grant Application Form |
Artificial Neural Networks have been successfully applied over the years to perform various tasks. However, in the absence of a successful theoretical analysis of neural network training for multi-layer perceptrons, most of the training methods used, as well as the setting of the training coefficients, are based on heuristic observations. One of the leading techniques in neural networks training, especially for large systems, is on-line learning of continuous functions via gradient descent in a differentiable error measure. This technique has been successfully applied in many real-world training problems and is arguably the most commonly used neural networks technique. A recent study, signalling a breakthrough in the analysis of on-line learning scenarios. This project, building directly on these developments as well as insights gained from earlier work, will focus on examining the effects of various types of noise on the learning process and the efficiency of regularisation techniques for improving network performance in on-line learning scenarios. In addition we will exploit the theoretical framework to examine analytically existing heuristic training techniques and to develop methods for improving the training process which will be demonstrated on real-world tasks.
|
Key Findings |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Potential use in non-academic contexts |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Impacts |
Description |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk |
Summary |
|
Date Materialised |
|
|
Sectors submitted by the Researcher |
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
|
Project URL: |
|
Further Information: |
|
Organisation Website: |
http://www.aston.ac.uk |