{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:07:24Z","timestamp":1725754044983},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642420412"},{"type":"electronic","value":"9783642420429"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-42042-9_17","type":"book-chapter","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T14:08:03Z","timestamp":1383055683000},"page":"132-139","source":"Crossref","is-referenced-by-count":1,"title":["Training Neural Networks with Implicit Variance"],"prefix":"10.1007","author":[{"given":"Justin","family":"Bayer","sequence":"first","affiliation":[]},{"given":"Christian","family":"Osendorfer","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Urban","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"van der Smagt","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"17_CR1","unstructured":"Wang, S., Manning, C.: Fast dropout training. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), pp. 118\u2013126 (2013)"},{"key":"17_CR2","first-page":"1106","volume":"25","author":"A. Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems\u00a025, 1106\u20131114 (2012)","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"17_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G.E. Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing\u00a020(1), 30\u201342 (2012)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Larochelle, H., Erhan, D., Courville, A., Bergstra, J., Bengio, Y.: An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning, pp. 473\u2013480. ACM (2007)","DOI":"10.1145\/1273496.1273556"},{"issue":"5786","key":"17_CR5","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G.E. Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science\u00a0313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642\u20133649. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Zeiler, M., Ranzato, M., Monga, R., Mao, M., Yang, K., Le, Q., Nguyen, P., Senior, A., Vanhoucke, V., Dean, J., et\u00a0al.: On rectified linear units for speech processing, ICASSP (2013)","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"17_CR8","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012)"},{"issue":"1","key":"17_CR9","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0004-3702(92)90065-6","volume":"56","author":"R.M. Neal","year":"1992","unstructured":"Neal, R.M.: Connectionist learning of belief networks. Artificial Intelligence\u00a056(1), 71\u2013113 (1992)","journal-title":"Artificial Intelligence"},{"key":"17_CR10","unstructured":"Bengio, Y., Thibodeau-Laufer, \u00c9.: Deep generative stochastic networks trainable by backprop (2013)"},{"issue":"6088","key":"17_CR11","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature\u00a0323(6088), 533\u2013536 (1986)","journal-title":"Nature"},{"key":"17_CR12","unstructured":"Tang, Y., Salakhutdinov, R.: A new learning algorithm for stochastic feedforward neural nets (2013)"},{"key":"17_CR13","first-page":"1305","volume":"arXiv","author":"Y. Bengio","year":"2013","unstructured":"Bengio, Y.: Estimating or propagating gradients through stochastic neurons. arXiv preprint arXiv:1305.2982 (2013)","journal-title":"arXiv preprint"},{"key":"17_CR14","first-page":"1249","volume":"20","author":"R. Salakhutdinov","year":"2008","unstructured":"Salakhutdinov, R., Hinton, G.: Using deep belief nets to learn covariance kernels for gaussian processes. Advances in Neural Information Processing Systems\u00a020, 1249\u20131256 (2008)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Uria, B., Murray, I., Renals, S., Richmond, K.: Deep architectures for articulatory inversion. In: Proceedings of Interspeech (2012)","DOI":"10.21437\/Interspeech.2012-263"},{"key":"17_CR16","unstructured":"Bishop, C.M.: Mixture density networks (1994)"},{"key":"17_CR17","unstructured":"Werbos, P.: Beyond regression: New tools for prediction and analysis in the behavioral sciences (1974)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Le Cun, Y.: Learning process in an asymmetric threshold network. In: Disordered Systems and Biological Organization, pp. 233\u2013240. Springer (1986)","DOI":"10.1007\/978-3-642-82657-3_24"},{"key":"17_CR19","volume-title":"Pattern recognition and machine learning","author":"C.M. Bishop","year":"2006","unstructured":"Bishop, C.M., et al.: Pattern recognition and machine learning, vol.\u00a01. Springer, New York (2006)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Julier, S.J., Uhlmann, J.K.: New extension of the kalman filter to nonlinear systems. In: AeroSense 1997 International Society for Optics and Photonics, pp. 182\u2013193 (1997)","DOI":"10.1117\/12.280797"},{"issue":"12","key":"17_CR21","doi-asserted-by":"publisher","first-page":"2602","DOI":"10.1162\/089976605774320557","volume":"17","author":"S. Vijayakumar","year":"2005","unstructured":"Vijayakumar, S., D\u2019souza, A., Schaal, S.: Incremental online learning in high dimensions. Neural Computation\u00a017(12), 2602\u20132634 (2005)","journal-title":"Neural Computation"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Rasmussen, C.E.: Gaussian processes for machine learning. Citeseer (2006)","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"17_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","volume-title":"Neural Networks: Tricks of the Trade","author":"Y.A. LeCun","year":"1998","unstructured":"LeCun, Y.A., Bottou, L., Orr, G.B., M\u00fcller, K.-R.: Efficient backProp. In: Orr, G.B., M\u00fcller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol.\u00a01524, pp. 9\u201350. Springer, Heidelberg (1998)"},{"key":"17_CR24","first-page":"281","volume":"13","author":"J. Bergstra","year":"2012","unstructured":"Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. The Journal of Machine Learning Research\u00a013, 281\u2013305 (2012)","journal-title":"The Journal of Machine Learning Research"},{"key":"17_CR25","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5 - rmsprop: Divide the gradient by a running average of its recent magnitude. In: COURSERA: Neural Networks for Machine Learning (2012)"},{"key":"17_CR26","unstructured":"Sutskever, I.: Training Recurrent Neural Networks. PhD thesis, University of Toronto (2013)"},{"key":"17_CR27","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning (2013)"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Le, Q.V., Smola, A.J., Canu, S.: Heteroscedastic gaussian process regression. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 489\u2013496. ACM (2005)","DOI":"10.1145\/1102351.1102413"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-42042-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T21:33:57Z","timestamp":1646948037000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-42042-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642420412","9783642420429"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-42042-9_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}