Domain Adaption Based on ELM Autoencoder
Open Access
- 1 January 2017
- journal article
- research article
- Published by Hindawi Limited in Mathematical Problems in Engineering
- Vol. 2017, 1-8
- https://doi.org/10.1155/2017/1239164
Abstract
We propose a new ELM Autoencoder (ELM-AE) based domain adaption algorithm which describes the subspaces of source and target domain by ELM-AE and then carries out subspace alignment to project different domains into a common new space. By leveraging nonlinear approximation ability and efficient one-pass learning ability of ELM-AE, the proposed domain adaption algorithm can efficiently seek a better cross-domain feature representation than linear feature representation approaches such as PCA to improve domain adaption performance. The widely experimental results on Office/Caltech-256 datasets show that the proposed algorithm can achieve better classification accuracy than PCA subspace alignment algorithm and other state-of-the-art domain adaption algorithms in most cases.Keywords
Funding Information
- National Natural Science Foundation of China (61572399, 61272120, 61373116, 2013KJXX-29)
This publication has 17 references indexed in Scilit:
- An empirical convolutional neural network approach for semantic relation classificationNeurocomputing, 2016
- New Trends of Learning in Computational Intelligence [Guest Editorial]IEEE Computational Intelligence Magazine, 2015
- Multi-dimensional extreme learning machineNeurocomputing, 2015
- Deep Extreme Learning Machine and Its Application in EEG ClassificationMathematical Problems in Engineering, 2015
- Trends in extreme learning machines: A reviewNeural Networks, 2015
- Stacked Extreme Learning MachinesIEEE Transactions on Cybernetics, 2014
- A fast and robust model selection algorithm for multi-input multi-output support vector machineNeurocomputing, 2014
- Learning With Augmented Features for Supervised and Semi-Supervised Heterogeneous Domain AdaptationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden NodesIEEE Transactions on Neural Networks, 2006
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995