{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T20:55:13Z","timestamp":1764276913740},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p>Although Deep Neural Networks (DNNs) have\u00a0achieved excellent performance in many tasks, improving the generalization capacity of DNNs still\u00a0remains a challenge. In this work, we propose a\u00a0novel regularizer named Ensemble-based Decorrelation Method (EDM), which is motivated by the\u00a0idea of the ensemble learning to improve generalization capacity of DNNs. EDM can be applied to\u00a0hidden layers in fully connected neural networks or\u00a0convolutional neural networks. We treat each hidden layer as an ensemble of several base learners\u00a0through dividing all the hidden units into several\u00a0non-overlap groups, and each group will be viewed\u00a0as a base learner. EDM encourages DNNs to learn\u00a0more diverse representations by minimizing the covariance between all base learners during the training step. Experimental results on MNIST and CIFAR datasets demonstrate that EDM can effectively\u00a0reduce the overfitting and improve the generalization capacity of DNNs\u00a0\u00a0<\/jats:p>","DOI":"10.24963\/ijcai.2018\/301","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"2177-2183","source":"Crossref","is-referenced-by-count":12,"title":["Regularizing Deep Neural Networks with an Ensemble-based Decorrelation Method"],"prefix":"10.24963","author":[{"given":"Shuqin","family":"Gu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexian","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Software, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2018","name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","start":{"date-parts":[[2018,7,13]]},"theme":"Artificial Intelligence","location":"Stockholm, Sweden","end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:51:35Z","timestamp":1530755495000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/301"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/301","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}