{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T16:22:56Z","timestamp":1751041376743},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319541839"},{"type":"electronic","value":"9783319541846"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-54184-6_13","type":"book-chapter","created":{"date-parts":[[2017,3,9]],"date-time":"2017-03-09T15:44:25Z","timestamp":1489074265000},"page":"205-220","source":"Crossref","is-referenced-by-count":7,"title":["Efficient Model Averaging for Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"Michael","family":"Opitz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Horst","family":"Possegger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Horst","family":"Bischof","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,10]]},"reference":[{"key":"13_CR1","first-page":"123","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L.: Bagging predictors. Mach. Learn. (ML) 24, 123\u2013140 (1996)","journal-title":"Mach. Learn. (ML)"},{"key":"13_CR2","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. (JCSS) 55, 119\u2013139 (1997)","journal-title":"J. Comput. Syst. Sci. (JCSS)"},{"key":"13_CR3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. (ML) 45, 5\u201332 (2001)","journal-title":"Mach. Learn. (ML)"},{"key":"13_CR4","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)"},{"key":"13_CR5","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (ICLR) (2014)"},{"key":"13_CR6","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. (JMLR) 15, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"13_CR7","unstructured":"Cogswell, M., Ahmed, F., Girshick, R.B., Zitnick, L., Batra, D.: Reducing overfitting in deep networks by decorrelating representations. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)"},{"key":"13_CR8","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the International Conference on Machine Learning (ICML) (2010)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"13_CR10","unstructured":"Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the International Conference on Machine Learning (ICML) (2013)"},{"key":"13_CR11","unstructured":"Goodfellow, I., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. In: Proceedings of the International Conference on Machine Learning (ICML) (2013)"},{"key":"13_CR12","unstructured":"Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)"},{"key":"13_CR13","unstructured":"Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J. (eds.) Field Guide to Dynamical Recurrent Neural Networks. IEEE Press (2001)"},{"key":"13_CR14","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"13_CR15","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. (2015). arXiv:1512.03385"},{"key":"13_CR16","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. (JMLR) 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"13_CR17","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5\u2013RmsProp: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning (2012)"},{"key":"13_CR18","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method (2012). http:\/\/arxiv.org\/abs\/1212.5701"},{"key":"13_CR19","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"13_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning (ICML) (2015)"},{"key":"13_CR21","unstructured":"Mishkin, D., Matas, J.: All you need is a good in it. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)"},{"key":"13_CR22","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Artificial Intelligence and Statistics Conference (AISTATS) (2010)"},{"key":"13_CR23","unstructured":"Kr\u00e4henb\u00fchl, P., Doersch, C., Donahue, J., Darrell, T.: Data-dependent initializations of convolutional neural networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"13_CR25","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics Conference (AISTATS) (2015)"},{"key":"13_CR26","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. In: Proceedings of the International Conference on Learning Representations (ICLR) (2014)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Sermanet, P., LeCun, Y.: Traffic sign recognition with multi-scale convolutional networks. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN) (2011)","DOI":"10.1109\/IJCNN.2011.6033589"},{"key":"13_CR28","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). http:\/\/arxiv.org\/abs\/1503.02531"},{"key":"13_CR29","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: FitNets: hints for thin deep nets. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)"},{"key":"13_CR30","unstructured":"Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropConnect. In: Proceedings of the International Conference on Machine Learning (ICML), JMLR Workshop and Conference Proceedings (2013)"},{"key":"13_CR31","unstructured":"Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. In: Proceedings of the International Conference on Learning Representations (ICLR) (2013)"},{"key":"13_CR32","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1016\/S0893-6080(99)00073-8","volume":"12","author":"Y Liu","year":"1999","unstructured":"Liu, Y., Yao, X.: Ensemble learning via negative correlation. Neural Netw. 12, 1399\u20131404 (1999)","journal-title":"Neural Netw."},{"key":"13_CR33","volume-title":"Pattern Classification","author":"RO Duda","year":"2001","unstructured":"Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)","edition":"2"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Ueda, N., Nakano, R.: Generalization error of ensemble estimators. In: Proceedings of the IEEE International Conference on Neural Networks (ICNN) (1996)","DOI":"10.1109\/ICNN.1996.548872"},{"key":"13_CR35","unstructured":"Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images (2009)"},{"key":"13_CR36","unstructured":"The Theano Development Team: Theano: a Python framework for fast computation of mathematical expressions (2016). arXiv.org\/abs\/1605.02688"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-54184-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,25]],"date-time":"2017-06-25T12:18:42Z","timestamp":1498393122000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-54184-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319541839","9783319541846"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-54184-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}