{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T00:13:18Z","timestamp":1725754398128},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642420535"},{"type":"electronic","value":"9783642420542"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-42054-2_55","type":"book-chapter","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T06:25:29Z","timestamp":1383027929000},"page":"442-449","source":"Crossref","is-referenced-by-count":17,"title":["Pushing Stochastic Gradient towards Second-Order Methods \u2013 Backpropagation Learning with Transformations in Nonlinearities"],"prefix":"10.1007","author":[{"given":"Tommi","family":"Vatanen","sequence":"first","affiliation":[]},{"given":"Tapani","family":"Raiko","sequence":"additional","affiliation":[]},{"given":"Harri","family":"Valpola","sequence":"additional","affiliation":[]},{"given":"Yann","family":"LeCun","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"2","key":"55_CR1","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\u00a010(2), 251\u2013276 (1998)","journal-title":"Neural Computation"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep big simple neural nets excel on handwritten digit recognition. CoRR, abs\/1003.0358 (2010)","DOI":"10.1162\/NECO_a_00052"},{"issue":"5786","key":"55_CR3","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":"55_CR4","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR, abs\/1207.0580 (2012)"},{"key":"55_CR5","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks (2012)"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Le Roux, N., Manzagol, P.A., Bengio, Y.: Topmoumoute online natural gradient algorithm. In: Advances in Neural Information Processing Systems 20, NIPS 2007 (2008)","DOI":"10.1162\/neco.2008.04-07-510"},{"key":"55_CR7","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\u201348. Springer, Heidelberg (1998)"},{"key":"55_CR8","unstructured":"Martens, J.: Deep learning via Hessian-free optimization. In: Proceedings of the 27th International Conference on Machine Learning, ICML (2010)"},{"key":"55_CR9","first-page":"924","volume":"22","author":"T. Raiko","year":"2012","unstructured":"Raiko, T., Valpola, H., LeCun, Y.: Deep learning made easier by linear transformations in perceptrons. Journal of Machine Learning Research - Proceedings Track\u00a022, 924\u2013932 (2012)","journal-title":"Journal of Machine Learning Research - Proceedings Track"},{"key":"55_CR10","unstructured":"Schraudolph, N.N.: Accelerated gradient descent by factor-centering decomposition. Technical Report IDSIA-33-98, Istituto Dalle Molle di Studi sull\u2019Intelligenza Artificiale (1998)"},{"key":"55_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/3-540-49430-8_11","volume-title":"Neural Networks: Tricks of the Trade","author":"N.N. Schraudolph","year":"1998","unstructured":"Schraudolph, N.N.: Centering neural network gradient factors. In: Orr, G.B., M\u00fcller, K.-R. (eds.) NIPS-WS 1996. LNCS, vol.\u00a01524, pp. 207\u2013548. Springer, Heidelberg (1998)"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Vatanen, T., Raiko, T., Valpola, H., LeCun, Y.: Pushing stochastic gradient towards second-order methods \u2013 backpropagation learning with transformations in nonlinearities (pre-print, 2013), http:\/\/arxiv.org\/abs\/1301.3476","DOI":"10.1007\/978-3-642-42054-2_55"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-42054-2_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T16:18:05Z","timestamp":1646929085000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-42054-2_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642420535","9783642420542"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-42054-2_55","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}