Fetching the paper…
Reading the bibliography…
The theoretical explanation for deep neural network (DNN) is still an open problem.
V. I. Oseledets, “A multiplicative ergodic theorem: Lyapunov characteristic numbers for dynamical systems,” Trans. Moscow Math. Soc
1968
Earlier work this paper cites.
F. Ledrappier and L.-S. Young, “Entropy formula for random transformation,” Probability Theory and Related Fields
1988
Earlier work this paper cites.
T. S. Parker and L. O. Chua, Practical Numerical Algorithms for Chaotic Systems
1989
Earlier work this paper cites.
A. Hoekstra, R. P. W. Duin, “On the nonlinearity of pattern classifiers,” in Proc. of IEEE International Conference on Pattern Recognition
1996
Earlier work this paper cites.
L. Arnold, Random Dynamical Systems
1998
Earlier work this paper cites.
M. Anthony and P. Bartlett, Neural Network Learning: Theoretical Foundations
1999
Earlier work this paper cites.
T. K. Ho and M. Basu, “Measuring the complexity of classification problems,” in Proc. of IEEE International Conference on Pattern Recognition
2000
Earlier work this paper cites.
K. Falconer, Fractal Geometry: Mathematical Foundations and Applications
2003
Earlier work this paper cites.
M. Basu and T. K. Ho, Data Complexity in Pattern Recognition
2006
Earlier work this paper cites.
M. Li and P. M. B. Vitanyi, An Introduction to Kolmogorov Complexity and Its Applications
2008
Cited alongside, same era.
A. S. Matveev and A. V. Savkin, Estimation and Control Over Communication Networks
2009
Cited alongside, same era.
N. G. de Bruijn, Asymptotic Methods in Analysis
2010
Cited alongside, same era.
T. Downarowicz, Entropy in Dynamical Systems
2011
Cited alongside, same era.
I. R. Shafarevich and M. Reid, Basic Algebraic Geometry 1: Varieties in Projective Space
2013
Cited alongside, same era.
F. Montufar, R. Pascanu, K. Cho, and Y. Bengio. “On the number of linear regions of deep neural networks.” in Proc. of Conference on Neural Information Processing (NIPS)
2014
Cited alongside, same era.
S. Hanneke, “The optimal sample complexity of PAC learning,” Journal of Machine Learning Research
2016
Later among the works it cites.
K. He, X. Zhang, S. Ren, and J. Sun. “Deep residual learning for image recognition.” in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition
2016
Later among the works it cites.
S. Mallat, “Understanding deep convolutional networks,” Philosophical Transactions of The Royal Society A
2016
Later among the works it cites.
B. Poole, S. Lahiri, M. Raghu, J. Sohl-Dickstein and S. Ganguli, “Exponential expressivity in deep neural networks through transient chaos,” in Proc. of International Conference on Neural Information Processing (NIPS)
2016
Later among the works it cites.
L. Dinh, R. Pascanu, S. Bengio and Y. Bengio, “Sharp minima can generalize for deep nets,” in Proc. of the 34th International Conference on Machine Learning (ICML)
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
A. C. Lorena and M. C. P. Souto, “On measuring the complexity of classification problems,” in Proc. of International Conference on Neural Information Processing (NIPS)
2015
Cited alongside, same era.
I. Goodfellow, Y. Bengio and A. Courville, Deep Learning
2016
Cited alongside, same era.
P. L. Bartlett, N. Harvey, C. Liaw and A. Mehrabian, “Nearly-tight VC-dimension and psedudodimension for piecewise linear neural networks,” preprint
Cited in the paper.
ImageNet. http://www.image-net.org
Cited in the paper.
2017
Later among the works it cites.
S. L. Huang, A. Makur, L. Zheng and G. W. Wornell, “An information-theoretic approach to universal feature selection in high-dimensional inference,” in Proc. of IEEE International Symposium of Information Theory (ISIT)
2017
Later among the works it cites.
S. Liang and R. Srikant, “Why deep neural networks for function approximation?” in Proc. of International Conference on Learning Representations (ICLR)
2017
Later among the works it cites.
C. Zhang, S. Bengio, M. Hardt, B. Recht and O. Vinyals, “Understanding deep learning requires rethinking generalization,” in Proc. of 5th International Conference on Learning Representations (ICLR)
2017
Later among the works it cites.