Deep learning
Yann LeCuna b c✉, Yoshua Bengiod e, Geoffrey E. Hintonf g h
- a1] Facebook AI Research, 770 Broadway, New York, New York 10003 USA. [2] New York University, 715 Broadway, New York, New York 10003, USA
- bFacebook AI Research, 770 Broadway, New York, 10003, New York, USA
- cNew York University, 715 Broadway, New York, 10003, New York, USA
- dDepartment of Computer Science and Operations Research Université de Montréal, Pavillon André-Aisenstadt, PO Box 6128 Centre-Ville STN Montréal, Quebec H3C 3J7, Canada
- eDepartment of Computer Science and Operations Research Université de Montréal, Pavillon André-Aisenstadt, PO Box 6128 Centre-Ville STN, Montréal, H3C 3J7, Quebec, Canada
- f1] Google, 1600 Amphitheatre Parkway, Mountain View, California 94043, USA. [2] Department of Computer Science, University of Toronto, 6 King's College Road, Toronto, Ontario M5S 3G4, Canada
- gDepartment of Computer Science, University of Toronto, 6 King's College Road, Toronto, M5S 3G4, Ontario, Canada
- hGoogle, 1600 Amphitheatre Parkway, Mountain View, 94043, California, USA
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.