Characterizing Computation in Artificial Neural Networks by their Diclique Covers and Forman-Ricci Curvatures

##plugins.themes.bootstrap3.article.main##

  •   Allen D. Parks

Abstract

The relationships between the structural topology of artificial neural networks, their computational flow, and their performance is not well understood. Consequently, a unifying mathematical framework that describes computational performance in terms of their underlying structure does not exist. This paper makes a modest contribution to understanding the structure-computational flow relationship in artificial neural networks from the perspective of the dicliques that cover the structure of an artificial neural network and the Forman-Ricci curvature of an artificial neural network’s connections. Special diclique cover digraph representations of artificial neural networks useful for network analysis are introduced and it is shown that such covers generate semigroups that provide algebraic representations of neural network connectivity.


Keywords: Neural Networks, Band Semigroup, Computational Divergence, Computational Flow, Dicliques, Digraph, Forman-Ricci Curvature

References

W. Rawat, and Z. Wang, “Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review”, Neural Computation, vol. 29, pp. 2352-2449, 2017. Doi:10.1162/NECO_a_00990

M. Chau, and H. Chen, “Incorporating Web Analysis into Neural Networks: An Example in Hopfield Net Searching”, IEEE Transactions on Systems, Man, and Cyberbnetics-Part C: Applications and Reviews, vol. 37, no. 3, pp. 352-358, 2007. Doi:10.1109/TRMCC.2007.893277

P. Lee, S. Hui, and A. Fong, “Neural Networks for Web Content Filtering”, IEEE Intelligent Systems, pp. 48-57, 2002. Doi:10.1109/MIS.2002.1039832

M. Mustafa, T. Allen, and K. Appiah, “A comparative review of dynamic neural networks and hidden Markov model methods for mobile on-device speech recognition”, Neural Comput & Applic, vol. 31 (Suppl 2), pp. S891-S899, 2019. Doi:10.1007/s0052 1-017-3028-2

D. Krotov, and J. Hopfield, “Unsupervised learning by competing hidden units”, PNAS, vol. 116, no. 16, pp. 7723-7731, 2019. Doi:10.1073/pnas.1820458116

S. Xie, A. Kirillov, R. Girschick, and H. He, “Exploring Randomly Wired Neural Networks for Image Recognition”, arXiv preprint arXiv:1904.01569v2 [cs.CV], 2019.

W. Guss, and R. Salakhutdinov, “On Characterizing the Capacity of Neural Networks using Algebraic Topology”, arXiv preprint arXiv:1802.04443v1 [cs.LG], 2018.

R. Haralick, “The Diclique Representation and Decomposition of Binary Relations”, Journal of the Association for Computing Machinery, vol. 24, no. 4, pp. 356-366, 1974.

M. Weber, E. Saucan, and J. Jost, “Characterizing complex networks with Forman-Ricci curvature and associated geometric flows”, Journal of Complex Networks, Vol. 5, No. 4, pp. 527-550, 2017. Doi:10.1093/comnet/cnw030

R. Sreejith, J. Jost, E. Saucan, and A. Samal, “Forman curvature for directed networks”, arXiv preprint arXiv:1605.04662v2 [q-bio.MN], 2017.

J. Howie, An Introduction to Semigroup Theory, Academic Press: London, 1976, pp. 95-103.

A. Clifford, and G. Preston, The Algebraic Theory of Semigroups, Volume I. American Mathematical Society: Providence, Rhode Island, 1961, pp. 23-26.

Downloads

Download data is not yet available.

##plugins.themes.bootstrap3.article.details##

How to Cite
[1]
Parks, A. 2020. Characterizing Computation in Artificial Neural Networks by their Diclique Covers and Forman-Ricci Curvatures. European Journal of Engineering Research and Science. 5, 2 (Feb. 2020), 171-177. DOI:https://doi.org/10.24018/ejers.2020.5.2.1689.