Abstract
In this paper we analyze connections between artificial neural networks, in particular multilayer perceptrons, and Łukasiewicz fuzzy logic. Theoretical results lead us to: connect Polynomial completeness and the study of input selection; use normal form of Łukasiewicz formulas to describe the structure of these multilayer perceptrons.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
P. Amato, A. Di Nola, B. Gerla, Neural networks and rational Łukasiewicz logic, in Fuzzy Information Processing Society, 2002. Proceedings. NAFIPS. 2002 Annual Meeting of the North American, IEEE (2002), pp. 506–510
A. Astorino, A. Frangioni, M. Gaudioso, E. Gorgone, Piecewise-quadratic approximations in convex numerical optimization. SIAM J. Optim. 21(4), 1418–1438 (2011)
A. Astorino, M. Gaudioso, Polyhedral separability through successive LP. J. Optim. Theory Appl. 112(2), 265–293 (2002)
F. Bayat, T.A. Johansen, A.A. Jalali, Flexible piecewise function evaluation methods based on truncated binary search trees and lattice representation in explicit MPC. IEEE Trans. Control Syst. Technol. 20(3), 632–640 (2012)
L.P. Belluce, A. Di Nola, G. Lenzi, Algebraic geometry for MV-algebras. J. Symb. Log. 79(04), 1061–1091 (2014)
L.M. Cabrer, L. Spada, MV-algebras, infinite dimensional polyhedra, and natural dualities. Arch. Math. Log. 1–22 (2016)
R.L. Cignoli, I.M. d’Ottaviano, D. Mundici, Algebraic Foundations of Many-Valued Reasoning, vol. 7 (Springer Science & Business Media, 2013)
J. de Jesús Rubio, A method with neural networks for the classification of fruits and vegetables. Soft Comput. 1–14 (2016)
S. Dhompongsa, V. Kreinovich, H.T. Nguyen, How to interpret neural networks in terms of fuzzy logic? (2001)
A. Di Nola, G. Lenzi, G. Vitale, Łukasiewicz equivalent neural networks, in Advances in Neural Networks (Springer, 2016), pp. 161–168
A. Di Nola, G. Lenzi, G. Vitale, Riesz-McNaughton functions and Riesz MV-algebras of nonlinear functions. Fuzzy Sets and Syst. (2016). https://doi.org/10.1016/j.fss.2016.03.003
A. Di Nola, A. Lettieri, On normal forms in Łukasiewicz logic. Arch. Math. Log. 43(6), 795–823 (2004)
R. DŁugosz, W. Pedrycz, Łukasiewicz fuzzy logic networks and their ultra low power hardware implementation. Neurocomputing 73(7), 1222–1234 (2010)
A. Fuduli, M. Gaudioso, G. Giallombardo, A DC piecewise affine model and a bundling technique in nonconvex nonsmooth minimization. Optim. Methods Softw. 19(1), 89–102 (2004)
A. Fuduli, M. Gaudioso, G. Giallombardo, Minimizing nonconvex nonsmooth functions via cutting planes and proximity control. SIAM J. Optim. 14(3), 743–756 (2004)
A. Fuduli, M. Gaudioso, E. Nurminski, A splitting bundle approach for non-smooth non-convex minimization. Optimization 64(5), 1131–1151 (2015)
B. Gerla, Rational Łukasiewicz logic and divisible MV-algebras. Neural Netw. World 10 (2001)
V. Kreinovich, H.T. Nguyen, S. Sriboonchitta, Need for data processing naturally leads to fuzzy logic (and neural networks): fuzzy beyond experts and beyond probabilities. Int. J. Intell. Syst. 31(3), 276–293 (2016)
V.Y. Kreinovich, Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem. Neural Netw. 4(3), 381–383 (1991)
V.Y. Kreinovich, C. Quintana, Neural networks: what non-linearity to choose (1991)
R.J. Kuo, P. Wu, C. Wang, Fuzzy neural networks for learning fuzzy if-then rules. Appl. Artif. Intell. 14(6), 539–563 (2000)
C. Leandro, H. Pita, L. Monteiro, Symbolic knowledge extraction from trained neural networks governed by Łukasiewicz logics, in Computational Intelligence (Springer, 2011), pp. 45–58
J. Łukasiewicz, Z zagadnień logiki i filozofii: pisma wybrane (Państwowe Wydawn, Naukowe, 1961)
R. McNaughton, A theorem about infinite-valued sentential logic. J. Symb. Log. 16(1), 1–13 (1951)
H. Niu, J. Wang, Financial time series prediction by a random data-time effective RBF neural network. Soft Comput. 18(3), 497–508 (2014)
V. Novák, I. Perfilieva, H.T. Nguyen, V. Kreinovich, Research on advanced soft computing and its applications. Soft Comput. A Fusion Found. Methodol. Appl. 8(4), 239–246 (2004)
S.-K. Oh, W. Pedrycz, H.-S. Park, Genetically optimized fuzzy polynomial neural networks. IEEE Trans. Fuzzy Syst. 14(1), 125–144 (2006)
R.A. Osegueda, C.M. Ferregut, M.J. George, J.M. Gutierrez, V. Kreinovich, Computational geometry and artificial neural networks: a hybrid approach to optimal sensor placement for aerospace NDE (1997)
S.K. Pal, S. Mitra, Multilayer perceptron, fuzzy sets, and classification. IEEE Trans. Neural Netw. 3(5), 683–697 (1992)
J. Park, Y. Kim, I. Eom, K. Lee, Economic load dispatch for piecewise quadratic cost function using hopfield neural network. IEEE Trans. Power Syst. 8(3), 1030–1038 (1993)
W. Pedrycz, Heterogeneous fuzzy logic networks: fundamentals and development studies. IEEE Trans. Neural Netw. 15(6), 1466–1481 (2004)
I. Perfilieva, Neural nets and normal forms from fuzzy logic point of view. Neural Netw. World 11(6), 627–638 (2001)
V. Ravi, H.-J. Zimmermann, A neural network and fuzzy rule base hybrid for pattern classification. Soft Comput. 5(2), 152–159 (2001)
R.K. Roul, S.R. Asthana, G. Kumar, Study on suitability and importance of multilayer extreme learning machine for classification of text data. Soft Comput. 1–18 (2016)
C.E. Shannon, A symbolic analysis of relay and switching circuits. Trans. Am. Inst. Electr. Eng. 57(12), 713–723 (1938)
L.A. Zadeh, Fuzzy sets. Inf. Control 8(3), 338–353 (1965)
H.-J. Zhang, N.-F. Xiao, Parallel implementation of multilayered neural networks based on map-reduce on cloud computing clusters. Soft Comput. 20(4), 1471–1483 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Nola, A.D., Vitale, G. (2020). Łukasiewicz Logic and Artificial Neural Networks. In: Kosheleva, O., Shary, S., Xiang, G., Zapatrin, R. (eds) Beyond Traditional Probabilistic Data Processing Techniques: Interval, Fuzzy etc. Methods and Their Applications. Studies in Computational Intelligence, vol 835. Springer, Cham. https://doi.org/10.1007/978-3-030-31041-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-31041-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31040-0
Online ISBN: 978-3-030-31041-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)