Deep learning

May 27, 2015
9 pages
Published in:
  • Nature 521 (2015) 436-444
  • Published: May 27, 2015

Citations per year

20152018202120242025020406080100120140
Abstract: (Springer)
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.
  • Computer science
  • Mathematics and computing
  • ImageNet classification with deep convolutional neural networks. In Proc
    • A. Krizhevsky
      ,
    • I. Sutskever
      ,
    • G. Hinton
      • Adv.Neural Inf.Process.Syst. 25 (2012) 1090-1098
  • Learning hierarchical features for scene labeling
    • C. Farabet
      ,
    • C. Couprie
      ,
    • L. Najman
      ,
    • Y. LeCun
      • IEEE Trans.Pattern Anal.Machine Intell. 35 (2013) 1915-1929
  • Joint training of a convolutional network and a graphical model for human pose estimation. In Proc
    • J. Tompson
      ,
    • A. Jain
      ,
    • Y. LeCun
      ,
    • C. Bregler
      • Adv.Neural Inf.Process.Syst. 27 (2014) 1799-1807
  • Strategies for training large scale neural network language models. In Proc. Automatic Speech Recognition and Understanding 196-201
    • T. Mikolov
      ,
    • A. Deoras
      ,
    • D. Povey
      ,
    • L. Burget
      ,
    • J. Cernocky
  • Deep neural networks for acoustic modeling in speech recognition
    • G. Hinton
      • IEEE Sig.Proc.Mag. 29 (2012) 82-97
  • Deep convolutional neural networks for LVCSR. In Proc. Acoustics, Speech and
    • T. Sainath
      ,
    • A.-R. Mohamed
      ,
    • B. Kingsbury
      ,
    • B. Ramabhadran
      • Signal Processing 8614 (2013) 8618
  • Ma, J
    • R.P. Sheridan
      ,
    • A. Liaw
      ,
    • G.E. Dahl
      ,
    • V. Svetnik
  • Kaggle. Higgs boson machine learning challenge. Kaggle
  • Connectomic reconstruction of the inner plexiform layer in the mouse retina
    • M. Helmstaedter
      • Nature 500 (2013) 168-174
  • Deep learning of the tissue-regulated splicing code. Bioinformatics 30, i121-i129 .CAS PubMed PubMed Central
    • M.K. Leung
      ,
    • H.Y. Xiong
      ,
    • L.J. Lee
      ,
    • B.J. Frey
  • The human splicing code reveals new insights into the genetic determinants of disease
    • H.Y. Xiong
      • Science 347 (2015) 6218
  • Natural language processing (almost) from scratch
    • R. Collobert
      • J.Machine Learning Res. 12 (2011) 2493-2537
  • Question answering with subgraph embeddings. In Proc. Empirical Methods in Natural Language Processing
    • A. Bordes
      ,
    • S. Chopra
      ,
    • J. Weston
  • On using very large target vocabulary for neural machine translation. In Proc. ACL-IJCNLP
    • S. Jean
      ,
    • K. Cho
      ,
    • R. Memisevic
      ,
    • Y. Bengio
  • & Le. Q. V. Sequence
    • Sutskever
      ,
    • O. I. Vinyals
      • Adv.Neural Inf.Process.Syst. 27 (2014) 3104-3112
  • The tradeoffs of large scale learning. In Proc
    • L. Bottou
      ,
    • O. Bousquet
      • Adv.Neural Inf.Process.Syst. 20 (2007) 161-168
  • Pattern Classification and Scene Analysis
    • R.O. Duda
      ,
    • P.E. Hart
  • Learning with Kernels (MIT Press,).MATH
    • B. Schölkopf
      ,
    • A. Smola
  • The curse of highly variable functions for local kernel machines. In Proc
    • Y. Bengio
      ,
    • O. Delalleau
      ,
    • N. Le Roux
      • Adv.Neural Inf.Process.Syst. 18 (2005) 107-114
  • Pandemonium: a paradigm for learning in mechanisation of thought processes. In Proc. Symposium on Mechanisation of Thought Processes 513-526
    • O.G. Selfridge
  • The Perceptron — A Perceiving
    • F. Rosenblatt
  • Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Harvard Univ
    • P. Werbos
  • Learning Logic Report TR-47 (MIT Press,)
    • D.B. Parker