Skip to main content
Top
Published in: New Generation Computing 2/2023

14-03-2023

Improving the Generalisation Ability of Neural Networks Using a Lévy Flight Distribution Algorithm for Classification Problems

Authors: Ehsan Bojnordi, Seyed Jalaleddin Mousavirad, Mahdi Pedram, Gerald Schaefer, Diego Oliva

Published in: New Generation Computing | Issue 2/2023

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

While multi-layer perceptrons (MLPs) remain popular for various classification tasks, their application of gradient-based schemes for training leads to some drawbacks including getting trapped in local optima. To tackle this, population-based metaheuristic methods have been successfully employed. Among these, Lévy flight distribution (LFD), which explores the search space through random walks based on a Lévy distribution, has shown good potential to solve complex optimisation problems. LFD uses two main components, the step length of the walk and the movement direction, for random walk generation to explore the search space. In this paper, we propose a novel MLP training algorithm based on the Lévy flight distribution algorithm for neural network-based pattern classification. We encode the network’s parameters (i.e., its weights and bias terms) into a candidate solution for LFD, and employ the classification error as fitness function. The network parameters are then optimised, using LFD, to yield an MLP that is trained to perform well on the classification task at hand. In an extensive set of experiments, we compare our proposed algorithm with a number of other approaches, including both classical algorithms and other metaheuristic approaches, on a number of benchmark classification problems. The obtained results clearly demonstrate the superiority of our LFD training algorithm.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Al-Betar, M.A., Awadallah, M.A., Doush, I.A., Alomari, O.A., Abasi, A.K., Makhadmeh, S.N., Alyasseri, Z.A.A.: Boosting the training of neural networks through hybrid metaheuristics. In: Cluster Computing, pp. 1–23 (2022) Al-Betar, M.A., Awadallah, M.A., Doush, I.A., Alomari, O.A., Abasi, A.K., Makhadmeh, S.N., Alyasseri, Z.A.A.: Boosting the training of neural networks through hybrid metaheuristics. In: Cluster Computing, pp. 1–23 (2022)
2.
go back to reference Aljarah, I., Faris, H., Mirjalili, S.: Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Comput. 22(1), 1–15 (2018) CrossRef Aljarah, I., Faris, H., Mirjalili, S.: Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Comput. 22(1), 1–15 (2018) CrossRef
3.
go back to reference Altay, O., Altay, E.V.: A novel hybrid multilayer perceptron neural network with improved grey wolf optimizer. In: Neural Computing and Applications, pp. 1–28 (2022) Altay, O., Altay, E.V.: A novel hybrid multilayer perceptron neural network with improved grey wolf optimizer. In: Neural Computing and Applications, pp. 1–28 (2022)
4.
go back to reference Asuncion, A., Newman, D.: UCI machine learning repository (2007) Asuncion, A., Newman, D.: UCI machine learning repository (2007)
5.
go back to reference Aydogdu, I., Carbas, S., Akin, A.: Effect of levy flight on the discrete optimum design of steel skeletal structures using metaheuristics. Steel Compos. Struct. 24(1), 93–112 (2017) CrossRef Aydogdu, I., Carbas, S., Akin, A.: Effect of levy flight on the discrete optimum design of steel skeletal structures using metaheuristics. Steel Compos. Struct. 24(1), 93–112 (2017) CrossRef
6.
go back to reference Battiti, R.: First-and second-order methods for learning: between steepest descent and Newton’s method. Neural Comput. 4(2), 141–166 (1992) CrossRef Battiti, R.: First-and second-order methods for learning: between steepest descent and Newton’s method. Neural Comput. 4(2), 141–166 (1992) CrossRef
7.
go back to reference Bidgoli, A.A., Komleh, H.E., Mousavirad, S.J.: Seminal quality prediction using optimized artificial neural network with genetic algorithm. In: 9th International Conference on Electrical and Electronics Engineering, pp. 695–699 (2015) Bidgoli, A.A., Komleh, H.E., Mousavirad, S.J.: Seminal quality prediction using optimized artificial neural network with genetic algorithm. In: 9th International Conference on Electrical and Electronics Engineering, pp. 695–699 (2015)
8.
go back to reference Boughrara, H., Chtourou, M., Amar, C.B., Chen, L.: Facial expression recognition based on a MLP neural network using constructive training algorithm. Multimedia Tools Appl. 75(2), 709–731 (2016) CrossRef Boughrara, H., Chtourou, M., Amar, C.B., Chen, L.: Facial expression recognition based on a MLP neural network using constructive training algorithm. Multimedia Tools Appl. 75(2), 709–731 (2016) CrossRef
9.
go back to reference Cantú-Paz, E., Kamath, C.: An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 35, 915–927 (2005) CrossRef Cantú-Paz, E., Kamath, C.: An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 35, 915–927 (2005) CrossRef
10.
go back to reference Carvalho, M., Ludermir, T.B.: An analysis of PSO hybrid algorithms for feed-forward neural networks training. In: 9th Brazilian Symposium on Neural Networks, pp. 6–11 (2006) Carvalho, M., Ludermir, T.B.: An analysis of PSO hybrid algorithms for feed-forward neural networks training. In: 9th Brazilian Symposium on Neural Networks, pp. 6–11 (2006)
11.
go back to reference Chauhan, N., Ravi, V., Chandra, D.K.: Differential evolution trained wavelet neural networks: application to bankruptcy prediction in banks. Expert Syst. Appl. 36, 7659–7665 (2009) CrossRef Chauhan, N., Ravi, V., Chandra, D.K.: Differential evolution trained wavelet neural networks: application to bankruptcy prediction in banks. Expert Syst. Appl. 36, 7659–7665 (2009) CrossRef
12.
go back to reference Dolatabadi, A.M., Pour, M.S., Rezaee, K., Ajarostaghi, S.S.M.: Applying machine learning for optimization of dehumidification strategy on the modified model for the non-equilibrium condensation in steam turbines. Eng. Anal. Bound. Elem. 145, 13–24 (2022) MathSciNetCrossRef Dolatabadi, A.M., Pour, M.S., Rezaee, K., Ajarostaghi, S.S.M.: Applying machine learning for optimization of dehumidification strategy on the modified model for the non-equilibrium condensation in steam turbines. Eng. Anal. Bound. Elem. 145, 13–24 (2022) MathSciNetCrossRef
13.
go back to reference Ebrahimpour-Komleh, H., Mousavirad, S.J.: Cuckoo optimization algorithm for feedforward neural network training. In: 21st Iranian Conference on Electrical Engineering (2013) Ebrahimpour-Komleh, H., Mousavirad, S.J.: Cuckoo optimization algorithm for feedforward neural network training. In: 21st Iranian Conference on Electrical Engineering (2013)
14.
go back to reference Emami, H., Alipour, M.M.: Chaotic local search-based levy flight distribution algorithm for optimizing ONU placement in fiber-wireless access network. Opt. Fiber Technol. 67, 102733 (2021) CrossRef Emami, H., Alipour, M.M.: Chaotic local search-based levy flight distribution algorithm for optimizing ONU placement in fiber-wireless access network. Opt. Fiber Technol. 67, 102733 (2021) CrossRef
15.
go back to reference Ewees, A.A., Elaziz, M.A., Alameer, Z., Ye, H., Jianhua, Z.: Improving multilayer perceptron neural network using chaotic grasshopper optimization algorithm to forecast iron ore price volatility. Resour. Policy 65, 101555 (2020) CrossRef Ewees, A.A., Elaziz, M.A., Alameer, Z., Ye, H., Jianhua, Z.: Improving multilayer perceptron neural network using chaotic grasshopper optimization algorithm to forecast iron ore price volatility. Resour. Policy 65, 101555 (2020) CrossRef
16.
go back to reference Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design (1996) Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design (1996)
17.
go back to reference Hamzehei, S., Akbarzadeh, O., Attar, H., Rezaee, K., Fasihihour, N., Khosravi, M.R.: Predicting the total unified Parkinson’s disease rating scale (UPDRS) based on ml techniques and cloud-based update. J. Cloud Comput. 12(1), 1–16 (2023) CrossRef Hamzehei, S., Akbarzadeh, O., Attar, H., Rezaee, K., Fasihihour, N., Khosravi, M.R.: Predicting the total unified Parkinson’s disease rating scale (UPDRS) based on ml techniques and cloud-based update. J. Cloud Comput. 12(1), 1–16 (2023) CrossRef
18.
go back to reference Houssein, E.H., Hassaballah, M., Ibrahim, I.E., AbdElminaam, D.S., Wazery, Y.M.: An automatic arrhythmia classification model based on improved marine predators algorithm and convolutions neural networks. Expert Syst. Appl. 187, 115936 (2022) CrossRef Houssein, E.H., Hassaballah, M., Ibrahim, I.E., AbdElminaam, D.S., Wazery, Y.M.: An automatic arrhythmia classification model based on improved marine predators algorithm and convolutions neural networks. Expert Syst. Appl. 187, 115936 (2022) CrossRef
19.
go back to reference Houssein, E.H., Saad, M.R., Hashim, F.A., Shaban, H., Hassaballah, M.: Lévy flight distribution: a new metaheuristic algorithm for solving engineering optimization problems. Eng. Appl. Artif. Intell. 94, 103731 (2020) CrossRef Houssein, E.H., Saad, M.R., Hashim, F.A., Shaban, H., Hassaballah, M.: Lévy flight distribution: a new metaheuristic algorithm for solving engineering optimization problems. Eng. Appl. Artif. Intell. 94, 103731 (2020) CrossRef
20.
go back to reference Ilonen, J., Kamarainen, J.-K., Lampinen, J.: Differential evolution training algorithm for feed-forward neural networks. Neural Process. Lett. 17(1), 93–105 (2003) CrossRef Ilonen, J., Kamarainen, J.-K., Lampinen, J.: Differential evolution training algorithm for feed-forward neural networks. Neural Process. Lett. 17(1), 93–105 (2003) CrossRef
21.
go back to reference Izci, D., Ekinci, S., Hekimoğlu, B.: Fractional-order PID controller design for buck converter system via hybrid lévy flight distribution and simulated annealing algorithm. Arab. J. Sci. Eng., 1–19 (2022) Izci, D., Ekinci, S., Hekimoğlu, B.: Fractional-order PID controller design for buck converter system via hybrid lévy flight distribution and simulated annealing algorithm. Arab. J. Sci. Eng., 1–19 (2022)
22.
go back to reference Jamil, M., Zepernick, H.-J.: Lévy flights and global optimization. In: Swarm Intelligence and Bio-inspired Computation, pp. 49–72. Elsevier, Amsterdam (2013) Jamil, M., Zepernick, H.-J.: Lévy flights and global optimization. In: Swarm Intelligence and Bio-inspired Computation, pp. 49–72. Elsevier, Amsterdam (2013)
23.
go back to reference Kaidi, W., Khishe, M., Mohammadi, M.: Dynamic levy flight chimp optimization. Knowl. Based Syst. 235, 107625 (2022) CrossRef Kaidi, W., Khishe, M., Mohammadi, M.: Dynamic levy flight chimp optimization. Knowl. Based Syst. 235, 107625 (2022) CrossRef
24.
go back to reference Karaboga, D., Akay, B., Ozturk, C.: Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks. In: International Conference on Modeling Decisions for Artificial Intelligence, pp. 318–329 (2007) Karaboga, D., Akay, B., Ozturk, C.: Artificial bee colony (ABC) optimization algorithm for training feed-forward neural networks. In: International Conference on Modeling Decisions for Artificial Intelligence, pp. 318–329 (2007)
25.
go back to reference Kh, R., Rasegh, G.M., Chagha, G.N., Haddania, J.: An intelligent diagnostic system for detection of hepatitis using multi-layer perceptron and colonial competitive algorithm. J. Math. Comput. Sci. 4(1), 237–245 (2012) Kh, R., Rasegh, G.M., Chagha, G.N., Haddania, J.: An intelligent diagnostic system for detection of hepatitis using multi-layer perceptron and colonial competitive algorithm. J. Math. Comput. Sci. 4(1), 237–245 (2012)
26.
go back to reference Koçkal, N., Aydoğdu, İ.: Estimation of rigidity of concrete based on multi parameters using artificial bee colony optimization method with levy flight distribution. Filomat 34(2) (2020) Koçkal, N., Aydoğdu, İ.: Estimation of rigidity of concrete based on multi parameters using artificial bee colony optimization method with levy flight distribution. Filomat 34(2) (2020)
27.
go back to reference Leema, N., Khanna Nehemiah, H., Kannan, A.: Neural network classifier optimization using differential evolution with global information and back propagation algorithm for clinical datasets. Appl. Soft Comput. 49, 834–844 (2016) CrossRef Leema, N., Khanna Nehemiah, H., Kannan, A.: Neural network classifier optimization using differential evolution with global information and back propagation algorithm for clinical datasets. Appl. Soft Comput. 49, 834–844 (2016) CrossRef
28.
go back to reference Ling, Y., Zhou, Y., Luo, Q.: Lévy flight trajectory-based whale optimization algorithm for global optimization. IEEE Access 5, 6168–6186 (2017) CrossRef Ling, Y., Zhou, Y., Luo, Q.: Lévy flight trajectory-based whale optimization algorithm for global optimization. IEEE Access 5, 6168–6186 (2017) CrossRef
29.
30.
go back to reference Mandischer, M.: A comparison of evolution strategies and backpropagation for neural network training. Neurocomputing 42, 87–117 (2002) CrossRefMATH Mandischer, M.: A comparison of evolution strategies and backpropagation for neural network training. Neurocomputing 42, 87–117 (2002) CrossRefMATH
31.
go back to reference Mirjalili, S.: The ant lion optimizer. Adv. Eng. Softw. 83, 80–98 (2015) CrossRef Mirjalili, S.: The ant lion optimizer. Adv. Eng. Softw. 83, 80–98 (2015) CrossRef
32.
go back to reference Mirjalili, S.: Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput. Appl. 27(4), 1053–1073 (2016) MathSciNetCrossRef Mirjalili, S.: Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput. Appl. 27(4), 1053–1073 (2016) MathSciNetCrossRef
33.
go back to reference Mirjalili, S.: SCA: a sine cosine algorithm for solving optimization problems. Knowl. Based Syst. 96, 120–133 (2016) CrossRef Mirjalili, S.: SCA: a sine cosine algorithm for solving optimization problems. Knowl. Based Syst. 96, 120–133 (2016) CrossRef
34.
go back to reference Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: International Joint Conferences on Artificial Intelligence Organization, vol. 89, pp. 762–767 (1989) Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: International Joint Conferences on Artificial Intelligence Organization, vol. 89, pp. 762–767 (1989)
35.
go back to reference Mora-Rubio, A., Alzate-Grisales, J.A., Arias-Garzón, D., Buriticá, J.I.P., Varón, C.F.J., Bravo-Ortiz, M.A., Arteaga-Arteaga, H.B., Hassaballah, M., Orozco-Arias, S., Isaza, G. et al.: Multi-subject identification of hand movements using machine learning. In: Sustainable Smart Cities and Territories, pp. 117–128. Springer, Berlin (2022) Mora-Rubio, A., Alzate-Grisales, J.A., Arias-Garzón, D., Buriticá, J.I.P., Varón, C.F.J., Bravo-Ortiz, M.A., Arteaga-Arteaga, H.B., Hassaballah, M., Orozco-Arias, S., Isaza, G. et al.: Multi-subject identification of hand movements using machine learning. In: Sustainable Smart Cities and Territories, pp. 117–128. Springer, Berlin (2022)
36.
go back to reference Moravvej, S.V., Mousavirad, S.J., Moghadam, M.H., Saadatmand, M.: An LSTM-based plagiarism detection via attention mechanism and a population-based approach for pre-training parameters with imbalanced classes. In: International Conference on Neural Information Processing, pp. 690–701 (2021) Moravvej, S.V., Mousavirad, S.J., Moghadam, M.H., Saadatmand, M.: An LSTM-based plagiarism detection via attention mechanism and a population-based approach for pre-training parameters with imbalanced classes. In: International Conference on Neural Information Processing, pp. 690–701 (2021)
37.
go back to reference Mousavirad, S.J., Bidgoli, A.A., Ebrahimpour-Komleh, H., Schaefer, G., Korovin, I.: An effective hybrid approach for optimising the learning process of multi-layer neural networks. In: International Symposium on Neural Networks, pp. 309–317 (2019) Mousavirad, S.J., Bidgoli, A.A., Ebrahimpour-Komleh, H., Schaefer, G., Korovin, I.: An effective hybrid approach for optimising the learning process of multi-layer neural networks. In: International Symposium on Neural Networks, pp. 309–317 (2019)
38.
go back to reference Mousavirad, S.J., Bidgoli, A.A., Komleh, H.E., Schaefer, G.: A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training. Int. J. Bio-Inspired Comput. 14(4), 227–236 (2019) CrossRef Mousavirad, S.J., Bidgoli, A.A., Komleh, H.E., Schaefer, G.: A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training. Int. J. Bio-Inspired Comput. 14(4), 227–236 (2019) CrossRef
39.
go back to reference Mousavirad, S.J., Gandomi, A.H., Homayoun, H.: A clustering-based differential evolution boosted by a regularisation-based objective function and a local refinement for neural network training. In: 2022 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8. IEEE (2022) Mousavirad, S.J., Gandomi, A.H., Homayoun, H.: A clustering-based differential evolution boosted by a regularisation-based objective function and a local refinement for neural network training. In: 2022 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8. IEEE (2022)
40.
go back to reference Mousavirad, S.J., Jalali, S.M.J., Ahmadian, S., Khosravi, A., Schaefer, G., Nahavandi, S.: Neural network training using a biogeography-based learning strategy. In: International Conference on Neural Information Processing, pp. 147–155 (2020) Mousavirad, S.J., Jalali, S.M.J., Ahmadian, S., Khosravi, A., Schaefer, G., Nahavandi, S.: Neural network training using a biogeography-based learning strategy. In: International Conference on Neural Information Processing, pp. 147–155 (2020)
41.
go back to reference Mousavirad, S.J., Rahnamayan, S.: Evolving feedforward neural networks using a quasi-opposition-based differential evolution for data classification. In: IEEE Symposium Series on Computational Intelligence, pp. 2320–2326 (2020) Mousavirad, S.J., Rahnamayan, S.: Evolving feedforward neural networks using a quasi-opposition-based differential evolution for data classification. In: IEEE Symposium Series on Computational Intelligence, pp. 2320–2326 (2020)
42.
go back to reference Mousavirad, S.J., Schaefer, G., Ebrahimpour-Komleh, H.: Optimising connection weights in neural networks using a memetic algorithm incorporating chaos theory. In: Metaheuristics in Machine Learning: Theory and Applications, pp. 169–192. Springer, Berlin (2021) Mousavirad, S.J., Schaefer, G., Ebrahimpour-Komleh, H.: Optimising connection weights in neural networks using a memetic algorithm incorporating chaos theory. In: Metaheuristics in Machine Learning: Theory and Applications, pp. 169–192. Springer, Berlin (2021)
43.
go back to reference Mousavirad, S.J., Schaefer, G., Jalali, S.M.J., Korovin, I.: A benchmark of recent population-based metaheuristic algorithms for multi-layer neural network training. In: Genetic and Evolutionary Computation Conference Companion, pp. 1402–1408 (2020) Mousavirad, S.J., Schaefer, G., Jalali, S.M.J., Korovin, I.: A benchmark of recent population-based metaheuristic algorithms for multi-layer neural network training. In: Genetic and Evolutionary Computation Conference Companion, pp. 1402–1408 (2020)
44.
go back to reference Mousavirad, S.J., Schaefer, G., Korovin, I., Oliva, D.: RDE-OP: a region-based differential evolution algorithm incorporation opposition-based learning for optimising the learning process of multi-layer neural networks. In: International Conference on the Applications of Evolutionary Computation, pp. 407–420 (2021) Mousavirad, S.J., Schaefer, G., Korovin, I., Oliva, D.: RDE-OP: a region-based differential evolution algorithm incorporation opposition-based learning for optimising the learning process of multi-layer neural networks. In: International Conference on the Applications of Evolutionary Computation, pp. 407–420 (2021)
45.
go back to reference Mousavirad, S.J., Schaefer, G., Korovin, I.S.: An effective approach for neural network training based on comprehensive learning. In: 25th International Conference on Pattern Recognition, pp. 8774–8781 (2021) Mousavirad, S.J., Schaefer, G., Korovin, I.S.: An effective approach for neural network training based on comprehensive learning. In: 25th International Conference on Pattern Recognition, pp. 8774–8781 (2021)
46.
go back to reference Phansalkar, V.V., Sastry, P.S.: Analysis of the back-propagation algorithm with momentum. IEEE Trans. Neural Netw. 5(3), 505–506 (1994) CrossRef Phansalkar, V.V., Sastry, P.S.: Analysis of the back-propagation algorithm with momentum. IEEE Trans. Neural Netw. 5(3), 505–506 (1994) CrossRef
47.
go back to reference Piotrowski, A.P.: Differential evolution algorithms applied to neural network training suffer from stagnation. Appl. Soft Comput. 21, 382–406 (2014) CrossRef Piotrowski, A.P.: Differential evolution algorithms applied to neural network training suffer from stagnation. Appl. Soft Comput. 21, 382–406 (2014) CrossRef
49.
go back to reference Rather, S.A., Bala, P.S.: Lévy flight and chaos theory based gravitational search algorithm for multilayer perceptron training. In: Evolving Systems, pp. 1–28 (2022) Rather, S.A., Bala, P.S.: Lévy flight and chaos theory based gravitational search algorithm for multilayer perceptron training. In: Evolving Systems, pp. 1–28 (2022)
50.
go back to reference Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: IEEE International Conference on Neural Networks, pp. 586–591 (1993) Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: IEEE International Conference on Neural Networks, pp. 586–591 (1993)
51.
go back to reference Scales, L.E.: Introduction to Non-linear Optimization. Macmillan International Higher Education (1985) Scales, L.E.: Introduction to Non-linear Optimization. Macmillan International Higher Education (1985)
52.
go back to reference Sexton, R.S., Dorsey, R.E.: Reliable classification using neural networks: a genetic algorithm and backpropagation comparison. Decis. Support Syst. 30(1), 11–22 (2000) CrossRef Sexton, R.S., Dorsey, R.E.: Reliable classification using neural networks: a genetic algorithm and backpropagation comparison. Decis. Support Syst. 30(1), 11–22 (2000) CrossRef
53.
go back to reference Słowik, A., Bialko, M.: Training of artificial neural networks using differential evolution algorithm. In: Conference on Human System Interactions, pp. 60–65 (2008) Słowik, A., Bialko, M.: Training of artificial neural networks using differential evolution algorithm. In: Conference on Human System Interactions, pp. 60–65 (2008)
54.
go back to reference Tarkhaneh, O., Shen, H.: Training of feedforward neural networks for data classification using hybrid particle swarm optimization, mantegna lévy flight and neighborhood search. Heliyon 5(4), e01275 (2019) CrossRef Tarkhaneh, O., Shen, H.: Training of feedforward neural networks for data classification using hybrid particle swarm optimization, mantegna lévy flight and neighborhood search. Heliyon 5(4), e01275 (2019) CrossRef
55.
go back to reference Tuba, M., Alihodzic, A., Bacanin, N.: Cuckoo search and bat algorithm applied to training feed-forward neural networks. In: Recent Advances in Swarm Intelligence and Evolutionary Computation, pp. 139–162. Springer, Berlin (2015) Tuba, M., Alihodzic, A., Bacanin, N.: Cuckoo search and bat algorithm applied to training feed-forward neural networks. In: Recent Advances in Swarm Intelligence and Evolutionary Computation, pp. 139–162. Springer, Berlin (2015)
56.
go back to reference Yaghini, M., Khoshraftar, M.M., Fallahi, M.: A hybrid algorithm for artificial neural network training. Eng. Appl. Artif. Intell. 26, 293–301 (2013) CrossRef Yaghini, M., Khoshraftar, M.M., Fallahi, M.: A hybrid algorithm for artificial neural network training. Eng. Appl. Artif. Intell. 26, 293–301 (2013) CrossRef
57.
go back to reference Yang, X.-S., Deb, S.: Cuckoo search via Lévy flights. In: World Congress on Nature and Biologically Inspired Computing, pp. 210–214 (2009) Yang, X.-S., Deb, S.: Cuckoo search via Lévy flights. In: World Congress on Nature and Biologically Inspired Computing, pp. 210–214 (2009)
58.
go back to reference Yang, X.-S., Karamanoglu, M.: Swarm intelligence and bio-inspired computation: an overview. In: Swarm Intelligence and Bio-Inspired Computation, pp. 3–23 (2013) Yang, X.-S., Karamanoglu, M.: Swarm intelligence and bio-inspired computation: an overview. In: Swarm Intelligence and Bio-Inspired Computation, pp. 3–23 (2013)
Metadata
Title
Improving the Generalisation Ability of Neural Networks Using a Lévy Flight Distribution Algorithm for Classification Problems
Authors
Ehsan Bojnordi
Seyed Jalaleddin Mousavirad
Mahdi Pedram
Gerald Schaefer
Diego Oliva
Publication date
14-03-2023
Publisher
Springer Japan
Published in
New Generation Computing / Issue 2/2023
Print ISSN: 0288-3635
Electronic ISSN: 1882-7055
DOI
https://doi.org/10.1007/s00354-023-00214-5

Other articles of this Issue 2/2023

New Generation Computing 2/2023 Go to the issue

Premium Partner