Fetching the paper…
Reading the bibliography…
We propose a novel activation function that implements piece-wise orthogonal non-linear mappings based on permutations.
Multilevel assembly neural architecture and processing of sequences
EM Kussul and DA Rachkovskij · 1991
Earlier work this paper cites.
Untersuchungen zu dynamischen neuronalen netzen
S. Hochreiter · 1991
Earlier work this paper cites.
Learning long-term dependencies with gradient descent is difficult
P. Frasconi Y. Bengio, P. Simard · 1994
Earlier work this paper cites.
Long short-term memory
J. Schmidhuber S. Hochreiter · 1997
Earlier work this paper cites.
Reducing the dimensionality of data with neural networks
G.E. Hinton and R.R. Salakhutdinov · 2006
Earlier work this paper cites.
Deep, big, simple neural nets for handwritten digit recognition
J. Schmidhuber D.C. Ciresan, U. Meier L.M. Gambardella · 2010
Earlier work this paper cites.
Understanding the difficulty of training deep feedforward neural networks
Y. Bengio X. Glorot · 2010
Earlier work this paper cites.
Advanced Methods for Time Series Prediction Using Recurrent Neural Networks
H. Cardot R. Bone · 2011
Earlier work this paper cites.
Deep sparse rectifier neural networks
Y. Bengio X. Glorot, A. Bordes · 2011
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
G.E. Hinton A. Krizhevsky, I. Sutskever · 2012
Cited alongside, same era.
Long short-term memory in echo state networks: Details of a simulation study
H. Jaeger · 2012
Cited alongside, same era.
On the difficulty of training recurrent neural networks
Y. Bengio R. Pascanu · 2012
Cited alongside, same era.
Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
S. Ganguli A.M. Saxe, J.L. McClelland · 2013
Cited alongside, same era.
Dropout: A simple way to prevent neural networks from overfitting
A. Krizhevsky I. Sutskever R. Salakhutdinov N. Srivastava, G. Hinton · 2014
Later among the works it cites.
Deep residual learning for image recognition
S. Ren J. Sun K. He, X. Zhang · 2015
Later among the works it cites.
J. Matas D. Mishkin · 2015
Later among the works it cites.
A simple way to initialize recurrent networks of rectified linear units
G.E. Hinton Q.V. Le, N. Jaitly · 2015
Later among the works it cites.
Data-dependent initializations of convolutional neural networks
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
M. Mirza A. Courville Y. Bengio I.J. Goodfellow, D. Warde-Farley · 2013
Cited alongside, same era.
Advances in optimizing recurrent networks
R. Pascanu Y. Bengio, N. Boulanger-Lewandowski · 2013
Cited alongside, same era.
Return of the devil in the details: Delving deep into convolutional nets
A. Vedaldi A. Zisserman K. Chatfield, K. Simonyan · 2014
Cited alongside, same era.
J. Donahue T. Darrell P. Krhenbhl, C. Doersch · 2015
Later among the works it cites.
Fast and accurate deep network learning by exponential linear units (elus)
S. Hochreiter D.-A. Clevert, T. Unterthiner · 2015
Later among the works it cites.
Unitary evolution recurrent neural networks
Martin Arjovsky, Amar Shah, and Yoshua Bengio · 2015
Later among the works it cites.