{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:45:08Z","timestamp":1743097508922,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319235240"},{"type":"electronic","value":"9783319235257"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23525-7_22","type":"book-chapter","created":{"date-parts":[[2015,8,28]],"date-time":"2015-08-28T08:20:13Z","timestamp":1440750013000},"page":"359-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Sparse Bayesian Recurrent Neural Networks"],"prefix":"10.1007","author":[{"given":"Sotirios P.","family":"Chatzis","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,8,29]]},"reference":[{"key":"22_CR1","unstructured":"The CMU MoCap database. \n                      http:\/\/mocap.cs.cmu.edu\/"},{"issue":"2","key":"22_CR2","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S Amari","year":"1998","unstructured":"Amari, S.: Natural gradient works efficiently in learning. Neural Computation 10(2), 251\u2013276 (1998)","journal-title":"Neural Computation"},{"issue":"3","key":"22_CR3","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1016\/j.csl.2012.10.004","volume":"27","author":"J Barker","year":"2013","unstructured":"Barker, J., Vincent, E., Ma, N., Christensen, H., Green, P.: The Pascal Chime speech separation and recognition challenge. Computer Speech & Language 27(3), 621\u2013633 (2013)","journal-title":"Computer Speech & Language"},{"key":"22_CR4","unstructured":"Bastien, F., Lamblin, P., Pascanu, R., Bergstra, J., Goodfellow, I.J., Bergeron, A., Bouchard, N., Bengio, Y.: Theano: new features and speed improvements. In: Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop (2012)"},{"key":"22_CR5","unstructured":"Bayer, J., Osendorfer, C., Korhammer, D., Chen, N., Urban, S., van der Smagt, P.: On fast dropout and its applicability to recurrent networks. In: Proc. ICLR (2014)"},{"issue":"2","key":"22_CR6","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"52","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks 52(2), 157\u2013166 (1994)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: High-dimensional sequence transduction. In: Proc. ICASSP, pp. 3178\u20133182 (2013)","DOI":"10.1109\/ICASSP.2013.6638244"},{"issue":"9","key":"22_CR8","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/TNN.2011.2162109","volume":"22","author":"S Chatzis","year":"2011","unstructured":"Chatzis, S., Demiris, Y.: Echo state Gaussian process. IEEE Transactions on Neural Networks 22(9), 1435\u20131445 (2011)","journal-title":"IEEE Transactions on Neural Networks"},{"key":"22_CR9","unstructured":"Cotter, A., Shamir, O., Srebro, N., Sridharan, K.: Better mini-batch algorithms via accelerated gradient methods. In: Proc. NIPS (2011)"},{"key":"22_CR10","unstructured":"Fokoue, E.: Stochastic determination of the intrinsic structure in Bayesian factor analysis. Tech. Rep. TR-2004-17, Statistical and Applied Mathematical Sciences Institute (2004)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Proc. ICASSP (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"1","key":"22_CR12","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/S0925-2312(99)00174-5","volume":"31","author":"B Hammer","year":"2000","unstructured":"Hammer, B.: On the approximation capability of recurrent neural networks. Neurocomputing 31(1), 107\u2013123 (2000)","journal-title":"Neurocomputing"},{"issue":"8","key":"22_CR13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation 9(8), 1735\u20131780 (1997)","journal-title":"Neural Computation"},{"issue":"5","key":"22_CR14","first-page":"1303","volume":"14","author":"M Hoffman","year":"2013","unstructured":"Hoffman, M., Blei, D.M., Wang, C., Paisley, J.: Stochastic variational inference. Journal of Machine Learning Research 14(5), 1303\u20131347 (2013)","journal-title":"Journal of Machine Learning Research"},{"key":"22_CR15","unstructured":"Jaeger, H.: The \u201cecho state\u201d approach to analysing and training recurrent neural networks. Tech. Rep. 148, German National Research Center for Information Technology, Bremen (2001)"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Lan, G.: An optimal method for stochastic composite optimization. Mathematical Programming, 1\u201333 (2010)","DOI":"10.1007\/s10107-010-0434-y"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Martens, J., Sutskever, I.: Learning recurrent neural networks with hessian-free optimization. In: Proc. ICML (2011)","DOI":"10.1007\/978-3-642-35289-8_27"},{"key":"22_CR18","first-page":"372","volume":"27","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method of solving a convex programming problem with convergence rate $$o(1\/sqr(k))$$. Soviet Mathematics Doklady 27, 372\u2013376 (1983)","journal-title":"Soviet Mathematics Doklady"},{"key":"22_CR19","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: Proc. ICML (2013)"},{"issue":"5","key":"22_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"B Polyak","year":"1964","unstructured":"Polyak, B.: Some methods of speeding up the convergence of iteration methods. USSR Computational Mathematics and Mathematical Physics 4(5), 1\u201317 (1964)","journal-title":"USSR Computational Mathematics and Mathematical Physics"},{"key":"22_CR21","unstructured":"Ranganath, R., Gerrish, S., Blei, D.M.: Black box variational inference. In: Proc. AISTATS (2014)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Parallel Dist. Proc., pp. 318\u2013362. MIT Press (1986)","DOI":"10.21236\/ADA164453"},{"issue":"6","key":"22_CR23","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. Machine Learning Research 15(6), 1929\u20131958 (2014)","journal-title":"J. Machine Learning Research"},{"key":"22_CR24","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proc. ICML (2013)"},{"issue":"2","key":"22_CR25","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TPAMI.2007.1167","volume":"30","author":"JM Wang","year":"2008","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(2), 283\u2013298 (2008)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23525-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:06:27Z","timestamp":1599437187000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-23525-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319235240","9783319235257"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23525-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"29 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}