@article { , title = {Deep heterogeneous ensemble.}, abstract = {In recent years, deep neural networks (DNNs) have emerged as a powerful technique in many areas of machine learning. Although DNNs have achieved great breakthrough in processing images, video, audio and text, it also has some limitations such as needing a large number of labeled data for training and having a large number of parameters. Ensemble learning, meanwhile, provides a learning model by combining many different classifiers such that an ensemble of classifiers is better than using single classifier. In this study, we propose a deep ensemble framework called Deep Heterogeneous Ensemble (DHE) for supervised learning tasks. In each layer of our algorithm, the input data is passed through a feature selection method to remove irrelevant features and prevent overfitting. The cross-validation with K learning algorithms is applied to the selected data, in order to obtain the meta-data and the K base classifiers for the next layer. In this way, one layer will output the meta-data as the input data for the next layer, the base classifiers, and the indices of the selected meta-data. A combining algorithm is then applied on the meta-data of the last layer to obtain the final class prediction. Experiments on 30 datasets confirm that the proposed DHE is better than a number of well-known benchmark algorithms.}, conference = {26th International conference on neural information processing (ICONIP 2019)}, eissn = {1321-2133}, issn = {1321-2133}, issue = {1}, journal = {Australian journal of intelligent information processing systems}, note = {INFO COMPLETE (permissions confirmed, no rights retained by journal as long as VOR used and journal cited, so marked as Gold OA with APC covered by conference 06.05.2020 GB -- contact updated us with ISSN, also revealed that journal usually has APC. Need to contact editor to establish whether journal terms of use are sufficiently open to be counted as "Gold OA" 05.05.2020 GB -- rec'd from contact 04.05.2020 GB) PERMISSION GRANTED (version = VOR ; embargo = none ; licence = BY-NC ; e-mail, dated 05.05.2020 ; 06.05.2020 GB -- contacted editor tom@cs.anu.edu.au to ask about journal terms of use and self-archiving permissions; if sufficiently open to be counted as Gold, then can replace AAM with VoR and update repository licence accordingly 05.05.2020 GB -- need to contact journal editor to confirm permissions - http://ajiips.com.au/index.html 04.05.2020 GB) DOCUMENT READY (rec'd AAM from contact 04.05.2020 GB) ADDITIONAL INFO: Thanh Nguyen}, pages = {1-9}, publicationstatus = {Published}, publisher = {Australian Journal of Intelligent Processing Systems}, url = {https://rgu-repository.worktribe.com/output/905693}, volume = {16}, keyword = {Computational Intelligence (CI), Deep neural networks, Ensemble learning systems, Ensemble systems, Machine learning}, year = {2019}, author = {Nguyen, Tien Thanh and Dang, Manh Truong and Pham, Tien Dung and Dao, Lan Phuong and Luong, Anh Vu and McCall, John and Liew, Alan Wee Chung} }