@article{
 title = {Convolutional neural networks applied to house numbers digit classification},
 type = {article},
 year = {2012},
 pages = {3288-3291},
 publisher = {IEEE},
 id = {839ff939-d811-3e00-9799-bba441f44e03},
 created = {2022-09-19T09:01:25.259Z},
 file_attached = {true},
 profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2022-09-19T09:02:26.718Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
 private_publication = {false},
 abstract = {We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net. © 2012 ICPR Org Committee.},
 bibtype = {article},
 author = {Sermanet, Pierre and Chintala, Soumith and Lecun, Yann},
 journal = {Proceedings - International Conference on Pattern Recognition},
 number = {Icpr}
}

{"_id":"tdRxe8cjRJEAE3j68","bibbaseid":"sermanet-chintala-lecun-convolutionalneuralnetworksappliedtohousenumbersdigitclassification-2012","author_short":["Sermanet, P.","Chintala, S.","Lecun, Y."],"bibdata":{"title":"Convolutional neural networks applied to house numbers digit classification","type":"article","year":"2012","pages":"3288-3291","publisher":"IEEE","id":"839ff939-d811-3e00-9799-bba441f44e03","created":"2022-09-19T09:01:25.259Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-19T09:02:26.718Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100","private_publication":false,"abstract":"We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net. © 2012 ICPR Org Committee.","bibtype":"article","author":"Sermanet, Pierre and Chintala, Soumith and Lecun, Yann","journal":"Proceedings - International Conference on Pattern Recognition","number":"Icpr","bibtex":"@article{\n title = {Convolutional neural networks applied to house numbers digit classification},\n type = {article},\n year = {2012},\n pages = {3288-3291},\n publisher = {IEEE},\n id = {839ff939-d811-3e00-9799-bba441f44e03},\n created = {2022-09-19T09:01:25.259Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-19T09:02:26.718Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},\n private_publication = {false},\n abstract = {We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net. © 2012 ICPR Org Committee.},\n bibtype = {article},\n author = {Sermanet, Pierre and Chintala, Soumith and Lecun, Yann},\n journal = {Proceedings - International Conference on Pattern Recognition},\n number = {Icpr}\n}","author_short":["Sermanet, P.","Chintala, S.","Lecun, Y."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/6482ff0c-d62e-63a3-2fc8-c17e71586d6a/Convolutional_neural_networks_applied_to_house_numbers_digit_classification.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"sermanet-chintala-lecun-convolutionalneuralnetworksappliedtohousenumbersdigitclassification-2012","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["convolutional","neural","networks","applied","house","numbers","digit","classification","sermanet","chintala","lecun"],"title":"Convolutional neural networks applied to house numbers digit classification","year":2012}