On rectified linear units for speech processing
作者： M.D. Zeiler , M. Ranzato , R. Monga , M. Mao , K. Yang
DOI: 10.1109/ICASSP.2013.6638312
关键词: Vocabulary 、 Word (computer architecture) 、 Pattern recognition 、 Rectifier (neural networks) 、 Speech recognition 、 Artificial neural network 、 Initialization 、 Deep learning 、 Time delay neural network 、 Artificial intelligence 、 Speech processing 、 Computer science 、 Discriminative model
摘要: … ), and the units that compose the HDNN “rectified linear units” (… And finally, rectified linear units are faster to compute because … We conjecture that the reason why rectified linear units are …
matthewzeiler.com
toronto.edu 
stanford.edu 
utoronto.ca 参考文章(15)
Li Deng, Dong Yu, Brian Hutchinson, Parallel Training for Deep Stacking Networks. conference of the international speech communication association. pp. 2598- 2601 ,(2012)
Geoffrey E. Hinton, Vinod Nair, Rectified Linear Units Improve Restricted Boltzmann Machines international conference on machine learning. pp. 807- 814 ,(2010)
Christopher J. Rozell, Don H. Johnson, Richard G. Baraniuk, Bruno A. Olshausen, Sparse coding via thresholding and local competition in neural circuits Neural Computation. ,vol. 20, pp. 2526- 2563 ,(2008) , 10.1162/NECO.2008.03-07-486
Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, Auto-encoder bottleneck features using deep belief networks 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 4153- 4156 ,(2012) , 10.1109/ICASSP.2012.6288833
Christian Plahl, Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 4165- 4168 ,(2012) , 10.1109/ICASSP.2012.6288836
Geoffrey E. Hinton, Training products of experts by minimizing contrastive divergence Neural Computation. ,vol. 14, pp. 1771- 1800 ,(2002) , 10.1162/089976602760128018
Yann Lecun, Karol Gregor, Learning Fast Approximations of Sparse Coding international conference on machine learning. pp. 399- 406 ,(2010)
Yoshua Bengio, Xavier Glorot, Antoine Bordes, Deep Sparse Rectifier Neural Networks international conference on artificial intelligence and statistics. ,vol. 15, pp. 315- 323 ,(2011)
Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc'aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, Quoc Le, Andrew Ng, None, Large Scale Distributed Deep Networks neural information processing systems. ,vol. 25, pp. 1223- 1231 ,(2012)
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Yann LeCun, Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition arXiv: Computer Vision and Pattern Recognition. ,(2010)