Differential Evolution Algorithms Used to Optimize Weights of Neural Network Solving Pole-Balancing Problem
Differential evolution (DE) has been successfully used to solve difficult optimization problems. Every year, novel DE algorithms are developed to outperform the previous versions. The JADE is a famous DE algorithm using a mutation strategy current-to-pbest and the adaptation of control parameters. The SHADE has been developed to eliminate some bottlenecks of the JADE, especially its tendency to a premature convergence. The performance of these algorithms has been demonstrated on various benchmarks. The goal of this work is to compare the performance of the selected DE algorithms which are used to optimize the weights of the artificial neural network solving the pole-balancing problem.
KeywordsDifferential evolution JADE SHADE Artificial neural network Pole-balancing problem
The following grants are acknowledged for the financial support provided for this research by Grant of SGS No. 2018/177, VSB - Technical University of Ostrava and under the support of NAVY and MERLIN research lab.
- 2.Brownlee, J., et al.: The pole balancing problem: A Benchmark Control Theory Problem (2005)Google Scholar
- 5.Liang, J., Qu, B., Suganthan, P., Hernández-Díaz, A.G.: Problem definitions and evaluation criteria for the CEC 2013 special session on real-parameter optimization. In: Computational Intelligence Laboratory, Zhengzhou University, Zhengzhou, China and Nanyang Technological University, Singapore, Technical Report 201212, 3–18 (2013)Google Scholar
- 7.Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y.L., Tan, J., Le, Q., Kurakin, A.: Large-scale evolution of image classifiers. arXiv preprint. arXiv:1703.01041 (2017)
- 8.Slowik, A., Bialko, M.: Training of artificial neural networks using differential evolution algorithm. In: 2008 Conference on Human System Interactions, pp. 60–65. IEEE (2008)Google Scholar
- 10.Storn, R., Price, K.: Differential evolution-a simple and efficient adaptive scheme for global optimization over continuous spaces, vol. 3. ICSI, Berkeley (1995)Google Scholar
- 11.Suganthan, P.N., Hansen, N., Liang, J.J., Deb, K., Chen, Y.-P., Auger, A., Tiwari, S.: Problem definitions and evaluation criteria for the cec 2005 special session on real-parameter optimization. KanGAL report 2005005, 2005 (2005)Google Scholar
- 12.Tanabe, R., Fukunaga, A.: Success-history based parameter adaptation for differential evolution. In: 2013 IEEE Congress on Evolutionary Computation (CEC), pp. 71–78. IEEE (2013)Google Scholar
- 13.Tanabe, R., Fukunaga, A.S.: Improving the search performance of shade using linear population size reduction. In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 1658–1665. IEEE (2014)Google Scholar