Fetching the paper…
Reading the bibliography…
One of the central problems in the study of deep learning theory is to understand how the structure properties, such as depth, width and the number of nodes, affect the expressivity of deep neural networks.
Eran Malach and Shai Shalev-Shwartz, Is deeper better only when shallow is good?, arXiv:1903.03488
1903
Earlier work this paper cites.
1905
Earlier work this paper cites.
1912
Earlier work this paper cites.
OM Sharkovsky, Coexistence of the cycles of a continuous mapping of the line into itself, Ukrainskij matematicheskij zhurnal , 16(01)
1964
Earlier work this paper cites.
R. L. Adler, A. G. Konheim and M. H. McAndrew, Topological entropy, Transactions of the American Mathematical Society , 114
1965
Earlier work this paper cites.
OM Sharkovsky, On cycles and structure of continuous mapping, Ukrainskij matematicheskij zhurnal , 17(03)
1965
Earlier work this paper cites.
Michał Misiurewicz, Horseshoes for mappings of an interval, Bull. Acad. Pol. Sci., Ser. Sci. Math. , 27
1979
Earlier work this paper cites.
Michał Misiurewicz, Horseshoes for continuous mappings of an interval, Dynamical systems , (1980), 127–135
1980
Earlier work this paper cites.
Michał Misiurewicz and Wiesław Szlenk, Entropy of piecewise monotone mappings, Studia Math , 67
1980
Earlier work this paper cites.
1981
Cited alongside, same era.
Ian Parberry, Michael R. Garey, and Albert Meyer, Circuit complexity and neural networks, (1984), MIT Press
1984
Cited alongside, same era.
John Hastad, Almost optimal lower bounds for small depth circuits, In Proceedings of the eighteenth annual ACM symposium on Theory of computing , ACM (1986), 6–20
1986
Cited alongside, same era.
Johan Håstad, Computational limitations of small-depth circuits, (1987), MIT Press
1987
Cited alongside, same era.
George Cybenko, Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals and Systems , 2(4)
1989
Cited alongside, same era.
Michael Schmitt, Lower bounds on the complexity of approximating continuous functions by sigmoidal neural networks, In Advances in Neural Information Processing Systems , (2000), 328–334
2000
Later among the works it cites.
2003
Later among the works it cites.
Olivier Delalleau and Yoshua Bengio, Shallow vs. deep sum-product networks, In Advances in Neural Information Processing Systems , (2011), 666-674
2011
Later among the works it cites.
Guido F. Montufar, Razvan Pascanu, Kyunghyun Cho, and Yoshua Bengio, On the number of linear regions of deep neural networks, In Advances in Neural Information Processing Systems , (2014), 2294–2932
2014
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Ken-Ichi Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks , 2(3)
1989
Cited alongside, same era.
Kurt Hornik, Maxwell, Stinchcombe and Halbert White, Multilayer feedforward networks are universal approximators, Neural Networks , 2(5)
1989
Cited alongside, same era.
Andrew R. Barron, Approximation and estimation bounds for artificial neural networks, Machine Learning , 14(1)
1994
Cited alongside, same era.
Lluís Alsedà, Jaume Llibre, and Michał Misiurewicz, Combinatorial dynamics and entropy in dimension one, (2000)
2000
Cited alongside, same era.
Cited in the paper.
Cited in the paper.
Cited in the paper.
Benjamin Rossman, Rocco A. Servedio, and Li-Yang Tan, An average-case depth hierarchy theorem for boolean circuits, In Proceedings of the 2015 IEEE 56th Annual Symposium on Foundations of Computer Science (FOCS) , IEEE(2015),1030–1048
2015
Later among the works it cites.
Ronen Eldan and Ohad Shamir, The power of depth for feedforward neural networks, In Conference of learning theory , (2016), 907–940
2016
Later among the works it cites.
Ben Poole, Subhaneil Lahiri, Maithra Raghu, Jascha Sohl-Dickstein, and Surya Ganguli, Exponential expressivity in deep neural networks through transient chaos. In Advances in neural information processing systems, In Advances in Neural Information Processing Systems , (2016), 3360–3368
2016
Later among the works it cites.
Matus Telgarsky, benefits of depth in neural networks, In Conference on Learning Theory , (2016), 1517–1539
2016
Later among the works it cites.
Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, and Jascha Sohl Dickstein, On the expressive power of deep neural networks, In Proceedings of the 34th International Conference on Machine Learning , 70
2017
Later among the works it cites.