Abstract
In this chapter, we start with basic elements of Boolean expressions and circuit theory to define a background to study neural networks as computational models. We present the truth tables and algebra of propositions. Then, we consider the circuit theory since neural networks can be cast into the computational model formalized by circuit families. Specifically, the neural computation process can be organized in a graph or circuit whose gates (neurons) are arranged in layers. In this way, owing to the equivalence between circuits and Boolean expression approaches, we can discuss the universality of neural computing. We end this chapter with a discussion about elements from differential geometry and dynamical systems that are part of the mathematical background for our presentation. Specifically, we formalize a data model based on the concept of differentiable manifolds. Hence, the database samples and the associated probability density distribution occupy the natural place in the proposed data model. Dynamical systems foundations are necessary to visualize such data model in the context of Hamiltonian formalism when representing fluids as particle systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Henrik Reif Andersen. An introduction to binary decision diagrams. Lecture notes, available online, IT University of Copenhagen, page 5, 1997.
R. Beale and T. Jackson. Neural Computing. MIT Press, 1994.
John S. Bridle. Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. In NATO Neurocomputing, volume 68 of NATO ASI Series, pages 227–236. Springer, 1989.
Steven L. Brunton, Maziar S. Hemati, and Kunihiko Taira. Special issue on machine learning and data-driven methods in fluid dynamics. Theoretical and Computational Fluid Dynamics, 34(4):333–337, 2020.
Leandro Tavares da Silva and Gilson Antonio Giraldi. Fluid flow summarization technique for computational fluid dynamics analysis. In Computational Fluid Dynamics (CFD): Characteristics, Applications and Analysis, pages 1–44. Nova Science Publishers, 2016. Chapter 3.
Leonid Datta. A survey on activation functions and their relation with xavier and he normal initialization. CoRR, abs/2004.06632, 2020.
M.D. Davis and E.J. Weyuker. Computability, complexity, and languages: fundamentals of theoretical computer science. New York Academic Press, 1983.
M. do Carmo and P. Roitman. Geometria diferencial de curvas e superfícies. Textos Universitários. Sociedade Brasileira de Matemática, 2006.
Anselmo Ferreira and Gilson Giraldi. Convolutional neural network approaches to granite tiles classification. Expert Systems with Applications, 84:1–11, 2017.
A.T. Fomenko and S.P. Novikov. Modern geometry: Methods and Applications. New York: Springer-Verlag, 1992.
R. Garnier and J. Taylor. Discrete Mathematics for New Technology. Adam Hilger, 1992.
Gilson Antonio Giraldi. Machine Learning and Pattern Recognition, Lecture Notes - Graduate Program in Nanobiosystems, UFRJ-FIOCRUZ-INMETRO-LNCC, 2021.
H. Goldstein. Classical Mechanics. Addison-Wesley, 2nd edition, 1981.
I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. Adaptive Computation and Machine Learning series. MIT Press, 2016.
Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, and Gang Wang. Recent advances in convolutional neural networks. CoRR, abs/1512.07108, 2015.
Simon Haykin. Neural Networks - A Comprehensive Foundation, Second Edition. Prentice Hall, 2 edition, 1998.
Alan Julian Izenman. Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning. Springer Publishing Company, Incorporated, 1 edition, 2008.
S. Kong and M. Takatsuka. Hexpo: A vanishing-proof activation function. In 2017 International Joint Conference on Neural Networks (IJCNN), pages 2562–2567, 2017.
Alexander Kuleshov and Alexander Bernstein. Manifold learning in data mining tasks. In Machine Learning and Data Mining in Pattern Recognition: 10th International Conference, MLDM 2014, St. Petersburg, Russia, July 21–24, 2014. Proceedings 10, pages 119–133. Springer, 2014.
B. Laure, B. Angela, and M. Tova. Machine learning to data management: A round trip. In 2018 IEEE 34th International Conference on Data Engineering (ICDE), pages 1735–1738, 2018.
John A. Lee and Michel Verleysen. Nonlinear Dimensionality Reduction. Springer Publishing Company, Incorporated, 1st edition, 2007.
Yunqian Ma and Yun Fu. Manifold Learning Theory and Applications. CRC Press, Inc., Boca Raton, FL, USA, 1st edition, 2011.
Gastão Florencio Miranda, Carlos E. Thomaz, and Gilson A. Giraldi. Geometric data analysis based on manifold learning with applications for image understanding. 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images - Tutorials, pages 42–62, 2017.
Vinod Nair and Geoffrey E. Hinton. Rectified linear units improve restricted boltzmann machines. In ICML, pages 807–814. Omnipress, 2010.
KDnuggetsTM News. Six Steps to Master Machine Learning with Data Preparation, 2018.
M. Nielsen and I. Chuang. Quantum Computation and Quantum Information. Cambridge University Press., December 2000.
N. Pitelis, C. Russell, and L. Agapito. Learning a manifold as an atlas. In Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, June 2013.
John H. Reif and Stephen R. Tate. On threshold circuits and polynomial computation. SIAM J. Comput., 21(5):896–908, 1992.
Pulkit Sharma. A Comprehensive Tutorial to learn Convolutional Neural Networks from Scratch, 2018.
P. Tan, M. Steinbach, and V. Kumar. Introduction to Data Mining. Addison-Wesley, 2005.
J. Wang. Geometric Structure of High-Dimensional Data and Dimensionality Reduction. Springer Berlin Heidelberg, 2012.
Wikipedia. Activation Function. https://en.wikipedia.org/wiki/Activation_function, 2020.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Antonio Giraldi, G., Almeida, L.R.d., Lopes Apolinário Jr., A., Silva, L.T.d. (2023). Neural Networks Universality, Geometric, and Dynamical System Elements for Fluid Animation. In: Deep Learning for Fluid Simulation and Animation. SpringerBriefs in Mathematics. Springer, Cham. https://doi.org/10.1007/978-3-031-42333-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-42333-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42332-1
Online ISBN: 978-3-031-42333-8
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)