HYBRID NEURAL NETWORK OPTIMIZATION SYSTEM BASED ON ANT ALGORITHMS
DOI:
https://doi.org/10.18372/1990-5548.64.14857Keywords:
Multi-criteria optimization, ant algorithm, neural network, Pareto-optimalityAbstract
The ant multi-criteria algorithm for feed forward neural networks training is proposed. It is used two criteria: the error of generalization and complexity. It is represented a review of neural network learning using swarm algorithms. As a result of training it is determined a structure of neural network (a number of layers and neurons in then) and the values of weight coefficients and biases. Modification of well-known algorithms consists in using the concept of Pareto optimality. It is done the research of proposed algorithm on the example of multilayer perceptron for the approximation problem solution.
References
L. M. Gambardella, E. D. Taillard, and G. Agazzi, MACS-VRPTW: a multiple ant colony system for vehicle routing problems with time windows. In: Corne D, Dorigo M, Glover F, editors. New ideas in optimization. London: McGraw Hill; 1999, pp. 63–76.
S. Iredi, D. Merkle, and M. Middendorf, “Bi-criterion optimization with multi colony ant algorithms,” in: Zitzler E, Deb K, Thiele L, et al., editors. Vol. 1993, 1st International Conference on Evolutionary Multi-Criterion Optimization, (EMO’01), Lecture Notes in Computer Science. Heidelberg: Springer; 2001. pp. 359–372. https://doi.org/10.1007/3-540-44719-9_25
K. F. Doerner, W. J. Gutjahr, R. F. Hartl, et al., “Ant colony optimization in multiobjective portfolio selection,” in Proceedings of the Fourth Metaheuristics International Conference; 2001. pp. 243–248.
K. F. Doerner, W. J. Gutjahr, R. F. Hartl, et al., "Pareto ant colony optimization: a meta-heuristic approach to multiobjective portfolio selection," Annals of Operations Research, 2004;131:79–99. https://doi.org/10.1023/B:ANOR.0000039513.99038.c6
Manuel López-Ibáñez, Luís Paquete and Thomas Stützle, “On the Design of ACO for the Biobjective Quadratic Assignment Problem,” in Dorigo M., et al., editors, vol. 3172, Ant Colony Optimization and Swarm Intelligence: 4th International Workshop, ANTS 2004, Lecture Notes in Computer Science. Heidelberg: Springer; 2004. pp. 214–225. https://doi.org/10.1007/978-3-540-28646-2_19
Manuel López-Ibáñez, Luís Paquete, and Thomas Stützle, “Hybrid population-based algorithms for the bi-objective quadratic assignment problem,” J Math Model Algorithms, 2006, 5(1): 111–137. https://doi.org/10.1007/s10852-005-9034-x
C. Garcґıa-Martıґnez, O. Cordoґn, and F. Herrera, “A taxonomy and an empirical analysis of multiple objective ant colony optimization algorithms for the bi-criteria TSP,” Eur J Oper Res, 2007; 180(1):116–148. https://doi.org/10.1016/j.ejor.2006.03.041
K. F. Doerner, W. J. Gutjahr, R. F. Hartl, et al., “Nature-inspired metaheuristics in multiobjective activity crashing,” Omega, 2008, 36(6):1019–1037. https://doi.org/10.1016/j.omega.2006.05.001
M. Schilde, K. F. Doerner, R. F. Hartl, et al., “Metaheuristics for the bi-objective orienteering problem,” Swarm Intell, 2009, 3(3):179–201. https://doi.org/10.1007/s11721-009-0029-5
K. F. Doerner, R. F. Hartl, and M. Reimann, “Are CompetANTS more competent for problem solving? The case of a multiple objective transportation problem,” Cent Eur J Oper Res Econ, 2003, 11(2):115–141.
D. Angus, and C. Woodward, “Multiple objective ant colony optimization,” Swarm Intell, 2009, 3(1):69–85. https://doi.org/10.1007/s11721-008-0022-4
Rahul Karthik Sivagaminathan and Sreeram Ramakrishnan, “A hybrid approach for feature subset selection using neural networks and ant colony optimization,” Expert Systems with Applications: An International Journal, 33 (2007) 49–60. https://doi.org/10.1016/j.eswa.2006.04.010
F. Wan, F. Q. Wang, and W. L. Yuan, “The reservoir runoff forecast with artificial neural network based on ant colony optimization,” Applied ecology and environmental research 15(4): 497–510. https://doi.org/10.15666/aeer/1504_497510
Saman Sadeghyan and Shahrokh Asadi, MS-BACO: A new model selection algorithm using binary ant colony optimization for neural complexity and error reduction. Published 2018, Computer Science.
I. Alaya, C. Solnon, and K. Gheґdira, “Ant colony optimization for multi-objective optimization problems,” vol. 1, 19th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2007). Los Alamitos (CA): IEEE Computer Society Press; 2007, pp. 450–457. https://doi.org/10.1109/ICTAI.2007.108
Downloads
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
