{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T06:36:00Z","timestamp":1790145360912,"version":"4.0.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,5,17]],"date-time":"2012-05-17T00:00:00Z","timestamp":1337212800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["K\u00fcnstl Intell"],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1007\/s13218-012-0198-z","type":"journal-article","created":{"date-parts":[[2012,5,16]],"date-time":"2012-05-16T09:43:51Z","timestamp":1337161431000},"page":"357-363","source":"Crossref","is-referenced-by-count":78,"title":["Deep Learning"],"prefix":"10.1007","volume":"26","author":[{"given":"Hannes","family":"Schulz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Behnke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2012,5,17]]},"reference":[{"key":"198_CR1","first-page":"1356","volume-title":"Proceedings of international joint conference on neural networks (IJCNN)","author":"S Behnke","year":"1999","unstructured":"Behnke S (1999) Hebbian learning and competition in the neural abstraction pyramid. In: Proceedings of international joint conference on neural networks (IJCNN), Washington, DC, USA, vol\u00a02, pp\u00a01356\u20131361"},{"key":"198_CR2","first-page":"2758","volume-title":"Proceedings of international joint conference on neural networks (IJCNN)","author":"S Behnke","year":"2003","unstructured":"Behnke S (2003a) Discovering hierarchical speech features using convolutional non-negative matrix factorization. In: Proceedings of international joint conference on neural networks (IJCNN), Portland, Oregon, USA, vol\u00a04, pp\u00a02758\u20132763"},{"key":"198_CR3","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","DOI":"10.1007\/b11963","volume-title":"Hierarchical neural networks for image interpretation","author":"S Behnke","year":"2003","unstructured":"Behnke S (2003b) Hierarchical neural networks for image interpretation. Lecture notes in computer science, vol 2766. Springer, Berlin"},{"key":"198_CR4","first-page":"153","volume-title":"Advances in neural information processing systems (NIPS)","author":"Y Bengio","year":"2006","unstructured":"Bengio Y, Lamblin P, Popovici D, Larochelle H (2006) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems (NIPS), Vancouver, Canada, pp\u00a0153\u2013160"},{"key":"198_CR5","unstructured":"Bottou L (2011) From machine learning to machine reasoning. Arxiv preprint. arXiv:1102.1808"},{"key":"198_CR6","first-page":"2559","volume-title":"Proceedings of computer vision and pattern recognition (CVPR)","author":"Y Boureau","year":"2010","unstructured":"Boureau Y, Bach F, LeCun Y, Ponce J (2010) Learning mid-level features for recognition. In: Proceedings of computer vision and pattern recognition (CVPR), San Francisco, CA, USA, pp 2559\u20132566"},{"key":"198_CR7","doi-asserted-by":"crossref","unstructured":"Cire\u015fan DC, Meier U, Masci J, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: Proceedings of computer vision and pattern recognition (CVPR) (in press)","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"198_CR8","volume-title":"Proceedings of international conference on artificial intelligence and statistics (AISTATS)","author":"A Coates","year":"2010","unstructured":"Coates A, Lee H, Ng AY (2010) An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of international conference on artificial intelligence and statistics (AISTATS), Chia, Laguna, Italy"},{"key":"198_CR9","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1145\/1390156.1390177","volume-title":"Proceedings of international conference on machine learning (ICML)","author":"R Collobert","year":"2008","unstructured":"Collobert R, Weston J (2008) A unified architecture for natural language processing: deep neural networks with multitask learning. In: Proceedings of international conference on machine learning (ICML), Helsinki, Finland, pp 160\u2013167"},{"issue":"4","key":"198_CR10","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4):303\u2013314","journal-title":"Math. Control Signals Syst."},{"issue":"1","key":"198_CR11","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2012","unstructured":"Dahl G, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1):30\u201342","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"198_CR12","first-page":"153","volume-title":"Proceedings of international conference on artificial intelligence and statistics (AISTATS)","author":"D Erhan","year":"2009","unstructured":"Erhan D, Manzagol P, Bengio Y, Bengio S, Vincent P (2009) The difficulty of training deep architectures and the effect of unsupervised pre-training. In: Proceedings of international conference on artificial intelligence and statistics (AISTATS), Clearwater Beach, FL, USA, pp 153\u2013160"},{"key":"198_CR13","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan D, Bengio Y, Courville AC, Manzagol PA, Vincent P, Bengio S (2010) Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11:625\u2013660","journal-title":"J. Mach. Learn. Res."},{"key":"198_CR14","doi-asserted-by":"crossref","unstructured":"Fidler S, Leonardis A (2007) Towards scalable representations of object categories: learning a hierarchy of parts. In: Proceedings of computer vision and pattern recognition (CVPR), Minneapolis, MN, USA","DOI":"10.1109\/CVPR.2007.383269"},{"issue":"4","key":"198_CR15","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima K (1980) Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4):193\u2013202","journal-title":"Biol. Cybern."},{"key":"198_CR16","volume-title":"ICML deep learning workshop","author":"D Grangier","year":"2009","unstructured":"Grangier D, Bottou L, Collobert R (2009) Deep convolutional networks for scene parsing. In: ICML deep learning workshop, Montreal, Canada"},{"issue":"8","key":"198_CR17","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","volume":"14","author":"G Hinton","year":"2002","unstructured":"Hinton G (2002) Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8):1771\u20131800","journal-title":"Neural Comput."},{"issue":"5786","key":"198_CR18","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"G Hinton","year":"2006","unstructured":"Hinton G, Salakhutdinov R (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"7","key":"198_CR19","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"G Hinton","year":"2006","unstructured":"Hinton G, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput. 18(7):1527\u20131554","journal-title":"Neural Comput."},{"key":"198_CR20","volume-title":"A field guide to dynamical recurrent neural networks","author":"S Hochreiter","year":"2001","unstructured":"Hochreiter S, Bengio Y Frasconi P, Schmidhuber J (2001) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer SC, Kolen JF (eds) A field guide to dynamical recurrent neural networks. Wiley\/IEEE Press, New York"},{"key":"198_CR21","volume-title":"Proceedings of computer vision and pattern recognition (CVPR)","author":"J Huang","year":"1999","unstructured":"Huang J, Mumford D (1999) Statistics of natural images and models. In: Proceedings of computer vision and pattern recognition (CVPR), Ft. Collins, CO, USA"},{"key":"198_CR22","unstructured":"Kavukcuoglu K, Ranzato M, LeCun Y (2010) Fast inference in sparse coding algorithms with applications to object recognition. CoRR abs\/1010.3467"},{"issue":"4","key":"198_CR23","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4):541\u2013551","journal-title":"Neural Comput."},{"key":"198_CR24","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc. IEEE 86:2278\u20132324","journal-title":"Proc. IEEE"},{"key":"198_CR25","first-page":"609","volume-title":"Proceedings of international conference on machine learning (ICML)","author":"H Lee","year":"2009","unstructured":"Lee H, Grosse R, Ranganath R, Ng A (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proceedings of international conference on machine learning (ICML), New York, NY, USA, pp 609\u2013616"},{"key":"198_CR26","first-page":"1096","volume-title":"Advances in neural information processing systems (NIPS)","author":"H Lee","year":"2009","unstructured":"Lee H, Pham P, Largman Y, Ng A (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in neural information processing systems (NIPS), Vancouver, Canada, pp\u00a01096\u20131104"},{"key":"198_CR27","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1109\/ICCV.2011.6126419","volume-title":"Proceedings of international conference on computer vision (ICCV)","author":"R Memisevic","year":"2011","unstructured":"Memisevic R (2011) Gradient-based learning of higher-order image features. In: Proceedings of international conference on computer vision (ICCV), Barcelona, Spain, pp 1591\u20131598"},{"key":"198_CR28","first-page":"2551","volume-title":"Proceedings of computer vision and pattern recognition (CVPR)","author":"M Ranzato","year":"2010","unstructured":"Ranzato M, Hinton G (2010) Modeling pixel means and covariances using factorized third-order Boltzmann machines. In: Proceedings of computer vision and pattern recognition (CVPR), San Francisco, CA, USA, pp 2551\u20132558"},{"key":"198_CR29","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1038\/14819","volume":"2","author":"M Riesenhuber","year":"1999","unstructured":"Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat. Neurosci. 2:1019\u20131025","journal-title":"Nat. Neurosci."},{"issue":"6088","key":"198_CR30","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D Rumelhart","year":"1986","unstructured":"Rumelhart D, Hinton G, Williams R (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"key":"198_CR31","first-page":"92","volume-title":"Proceedings of international conference on artificial neural networks (ICANN)","author":"D Scherer","year":"2010","unstructured":"Scherer D, M\u00fcller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: Proceedings of international conference on artificial neural networks (ICANN), Thessaloniki, Greece, pp 92\u2013101"},{"key":"198_CR32","volume-title":"Proceedings of the European symposium on artificial neural networks (ESANN)","author":"H Schulz","year":"2012","unstructured":"Schulz H, Behnke S (2012) Learning object-class segmentation with convolutional neural networks. In: Proceedings of the European symposium on artificial neural networks (ESANN), Bruges, Belgium"},{"issue":"1","key":"198_CR33","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1002\/j.1538-7305.1949.tb03624.x","volume":"28","author":"C Shannon","year":"1949","unstructured":"Shannon C (1949) The synthesis of two-terminal switching circuits. Bell Syst. Tech. J. 28(1):59\u201398","journal-title":"Bell Syst. Tech. J."},{"key":"198_CR34","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1007\/978-3-642-15567-3_11","volume-title":"Computer Vision (ECCV 2010)","author":"G Taylor","year":"2010","unstructured":"Taylor G, Fergus R, LeCun Y, Bregler C (2010) Convolutional learning of spatio-temporal features. In: Computer Vision (ECCV 2010), pp\u00a0140\u2013153"},{"key":"198_CR35","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1145\/1390156.1390290","volume-title":"Proceedings of international conference on machine learning (ICML)","author":"T Tieleman","year":"2008","unstructured":"Tieleman T (2008) Training restricted Boltzmann machines using approximations to the likelihood gradient. In: Proceedings of international conference on machine learning (ICML), pp\u00a01064\u20131071"},{"issue":"7","key":"198_CR36","doi-asserted-by":"crossref","first-page":"1661","DOI":"10.1162\/NECO_a_00142","volume":"23","author":"P Vincent","year":"2011","unstructured":"Vincent P (2011) A connection between score matching and denoising autoencoders. Neural Comput. 23(7):1661\u20131674","journal-title":"Neural Comput."},{"key":"198_CR37","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11:3371\u20133408","journal-title":"J. Mach. Learn. Res."},{"key":"198_CR38","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1145\/1390156.1390303","volume-title":"Proceedings of international conference on machine learning (ICML)","author":"J Weston","year":"2008","unstructured":"Weston J, Ratle F, Collobert R (2008) Deep learning via semi-supervised embedding. In: Proceedings of international conference on machine learning (ICML), Helsinki, Finland, pp 1168\u20131175"},{"issue":"4","key":"198_CR39","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1162\/089976602317318938","volume":"14","author":"L Wiskott","year":"2002","unstructured":"Wiskott L, Sejnowski T (2002) Slow feature analysis: unsupervised learning of invariances. Neural Comput. 14(4):715\u2013770","journal-title":"Neural Comput."},{"key":"198_CR40","doi-asserted-by":"crossref","first-page":"2018","DOI":"10.1109\/ICCV.2011.6126474","volume-title":"Proceedings of international conference on computer vision (ICCV)","author":"M Zeiler","year":"2011","unstructured":"Zeiler M, Taylor G, Fergus R (2011) Adaptive deconvolutional networks for mid and high level feature learning. In: Proceedings of international conference on computer vision (ICCV), Barcelona, Spain, pp 2018\u20132025"}],"container-title":["KI - K\u00fcnstliche Intelligenz"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-012-0198-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13218-012-0198-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13218-012-0198-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T10:59:49Z","timestamp":1559473189000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13218-012-0198-z"}},"subtitle":["Layer-Wise Learning of Feature Hierarchies"],"short-title":[],"issued":{"date-parts":[[2012,5,17]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,11]]}},"alternative-id":["198"],"URL":"https:\/\/doi.org\/10.1007\/s13218-012-0198-z","relation":{},"ISSN":["0933-1875","1610-1987"],"issn-type":[{"value":"0933-1875","type":"print"},{"value":"1610-1987","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,5,17]]}}}