Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/120137
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | De Chazal, P. | - |
dc.contributor.author | McDonnell, M.D. | - |
dc.date.issued | 2016 | - |
dc.identifier.citation | Proceedings of International Joint Conference on Neural Networks, 2016, vol.2016-October, pp.68-75 | - |
dc.identifier.isbn | 9781509006199 | - |
dc.identifier.issn | 2161-4393 | - |
dc.identifier.issn | 2161-4407 | - |
dc.identifier.uri | http://hdl.handle.net/2440/120137 | - |
dc.description.abstract | An efficient algorithm for the calculation of the approximate Hessian matrix for the Levenberg-Marquardt (LM) optimization algorithm for training a single-hidden-layer feedforward network with linear outputs is presented. The algorithm avoids explicit calculation of the Jacobian matrix and computes the gradient vector and approximate Hessian matrix directly. It requires approximately 1/N the floating point operations of other published algorithms, where N is the number of network outputs. The required memory for the algorithm is also less than 1/N of the memory required for algorithms explicitly computing the Jacobian matrix. We applied our algorithm to two large-scale classification problems - the MNIST and the Forest Cover Type databases. Our results were within 0.5% of the best performance of systems using pixel values as inputs to a feedforward network for the MNIST database. Our results were achieved with a much smaller network than other published results. We achieved state-of-the-art performance for the Forest Cover Type database. | - |
dc.description.statementofresponsibility | Philip de Chazal, Mark D. McDonnell | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE International Joint Conference on Neural Networks (IJCNN) | - |
dc.rights | © 2016 IEEE | - |
dc.source.uri | http://dx.doi.org/10.1109/ijcnn.2016.7727182 | - |
dc.subject | Levenberg-Marquardt algorithm; feedforward neural networks; Gauss-Newton method; approximate Hessian calculation | - |
dc.title | Efficient computation of the Levenberg-Marquardt algorithm for feedforward networks with linear outputs | - |
dc.type | Conference paper | - |
dc.contributor.conference | International Joint Conference on Neural Networks (IJCNN) (24 Jul 2016 - 29 Jul 2016 : Vancouver, Canada) | - |
dc.identifier.doi | 10.1109/IJCNN.2016.7727182 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FT110101098 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/DP1093425 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | McDonnell, M.D. [0000-0002-7009-3869] | - |
Appears in Collections: | Aurora harvest 8 Electrical and Electronic Engineering publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.