65 lines
2.0 KiB
BibTeX
65 lines
2.0 KiB
BibTeX
|
@inproceedings{maas2013rectifier,
|
||
|
|
title={Rectifier nonlinearities improve neural network acoustic models},
|
||
|
|
author={Maas, Andrew L and Hannun, Awni Y and Ng, Andrew Y},
|
||
|
|
booktitle={Proc. ICML},
|
||
|
|
volume={30},
|
||
|
|
number={1},
|
||
|
|
year={2013}
|
||
|
|
}
|
||
|
|
|
||
|
|
@inproceedings{nair2010rectified,
|
||
|
|
title={Rectified linear units improve restricted {Boltzmann} machines},
|
||
|
|
author={Nair, Vinod and Hinton, Geoffrey E},
|
||
|
|
booktitle={Proc ICML},
|
||
|
|
pages={807--814},
|
||
|
|
year={2010}
|
||
|
|
}
|
||
|
|
|
||
|
|
@article{clevert2015fast,
|
||
|
|
title={Fast and accurate deep network learning by exponential linear units ({ELU}s)},
|
||
|
|
author={Clevert, Djork-Arn{\'e} and Unterthiner, Thomas and Hochreiter, Sepp},
|
||
|
|
journal={arXiv preprint arXiv:1511.07289},
|
||
|
|
year={2015}
|
||
|
|
}
|
||
|
|
@article{klambauer2017self,
|
||
|
|
title={Self-Normalizing Neural Networks},
|
||
|
|
author={Klambauer, G{\"u}nter and Unterthiner, Thomas and Mayr, Andreas and Hochreiter, Sepp},
|
||
|
|
journal={arXiv preprint arXiv:1706.02515},
|
||
|
|
year={2017}
|
||
|
|
}
|
||
|
|
|
||
|
|
@article{cohen2017emnist,
|
||
|
|
title = {{EMNIST}: an extension of {MNIST} to handwritten letters},
|
||
|
|
author = {Cohen, G. and Afshar, S. and Tapson, J. and van Schaik, A.},
|
||
|
|
journal={arXiv preprint arXiv:1702.05373},
|
||
|
|
year={2017},
|
||
|
|
url = {https://arxiv.org/abs/1702.05373}
|
||
|
|
}
|
||
|
|
|
||
|
|
@inproceedings{kingma2015adam,
|
||
|
|
title = {Adam: A Method for Stochastic Optimization},
|
||
|
|
author = {Diederik P. Kingma and Jimmy Ba},
|
||
|
|
booktitle = {ICML},
|
||
|
|
year = {2015},
|
||
|
|
url = {https://arxiv.org/abs/1412.6980}
|
||
|
|
}
|
||
|
|
|
||
|
|
@article{tieleman2012rmsprop,
|
||
|
|
title={Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude},
|
||
|
|
author={Tieleman, T. and Hinton, G. E.},
|
||
|
|
journal={COURSERA: Neural Networks for Machine Learning},
|
||
|
|
volume={4},
|
||
|
|
number={2},
|
||
|
|
year={2012},
|
||
|
|
url = {https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf}
|
||
|
|
}
|
||
|
|
|
||
|
|
@inproceedings{ioffe2015batch,
|
||
|
|
title={Batch normalization: Accelerating deep network training by reducing internal covariate shift},
|
||
|
|
author={Ioffe, Sergey and Szegedy, Christian},
|
||
|
|
booktitle={ICML},
|
||
|
|
pages={448--456},
|
||
|
|
year={2015},
|
||
|
|
url = {http://proceedings.mlr.press/v37/ioffe15.html}
|
||
|
|
}
|