Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107265
Title: | A systematic algorithm to escape from local minima in training feed-forward neural networks | Authors: | Cheung, CC Xu, SS Ng, SC |
Issue Date: | 2016 | Source: | In Proceedings of 2016 International Joint Conference on Neural Networks (IJCNN), 24-29 July 2016, Vancouver, BC, Canada | Abstract: | A learning process is easily trapped into a local minimum when training multi-layer feed-forward neural networks. An algorithm called Wrong Output Modification (WOM) was proposed to help a learning process escape from local minima, but WOM still cannot totally solve the local minimum problem. Moreover, there is no performance analysis to show that the learning has a higher probability of converging to a global solution by using this algorithm. Additionally, the generalization performance of this algorithm was not investigated when the early stopping method of training is applied. Based on these limitations of WOM, we propose a new algorithm to ensure the learning can escape from local minima, and its performance is analyzed. We also test the generalization performance of this new algorithm when the early stopping method of training is applied. | Publisher: | Institute of Electrical and Electronics Engineers | ISBN: | 978-1-5090-0620-5 (Electronic) 978-1-5090-0621-2 (Print on Demand(PoD)) |
DOI: | 10.1109/IJCNN.2016.7727226 | Description: | 2016 International Joint Conference on Neural Networks (IJCNN), 24-29 July 2016, Vancouver, BC, Canada | Rights: | ©2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The following publication Chi-Chung Cheung, Sean Shensheng Xu and Sin-Chun Ng, "A systematic algorithm to escape from local minima in training feed-forward neural networks," 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada, 2016, pp. 396-402 is available at https://doi.org/10.1109/IJCNN.2016.7727226. |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Cheung_Systematic_Algorithm_Escape.pdf | Pre-Published version | 960.71 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.