The Research on Controlling the Iteration of Quantum-Inspired Evolutionary Algorithms for Artificial Neural Networks
From recent research on optimizing artificial neural networks (ANNs), quantum-inspired evolutionary algorithm (QEA) was proved to be an effective method to design an ANN with few connections and high classifications. Quantum-inspired evolutionary neural network (QENN) is a kind of evolving neural networks. Similar to other evolutionary algorithms, it is important to control the iteration of QENN, otherwise it will waste a lot of time when QENN has been convergent. This paper proposes an appropriate termination criterion to control the iteration of QENN. The proposed termination criterion is based on the probability of the best solution. Experiments about pattern classification on iris have been done to demonstrate the effectiveness and applicability of the termination criterion. The results show that the termination criterion proposed in this paper could control the iteration of QENN effectively and save a mass of computing time by decreasing the number of generations of QENN.
KeywordsQ-bit representation quantum-inspired evolutionary algorithms (QEA) quantum-inspired evolutionary neural network (QENN) termination criterion convergence
Unable to display preview. Download preview PDF.
- 3.Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving networks: Using the genetic algorithm with connectionist learning. Citeseer (1990)Google Scholar
- 4.Brown, M., Harris, C.J.: Neurofuzzy adaptive modelling and control. Prentice-Hall (1994)Google Scholar
- 5.Han, K.H., Kim, J.H.: Genetic quantum algorithm and its application to combinatorial optimization problem. In: Proceedings of the 2000 Congress on Evolutionary Computation, vol. 2, pp. 1354–1360. IEEE (2000)Google Scholar
- 16.Schaffer, J.D., Whitley, D., Eshelman, L.J.: Combinations of genetic algorithms and neural networks: A survey of the state of the art. In: International Workshop on Combinations of Genetic Algorithms and Neural Networks, COGANN 1992, pp. 1–37. IEEE (1992)Google Scholar
- 22.Zhang, R., Gao, H.: Improved quantum evolutionary algorithm for combinatorial optimization problem. In: 2007 International Conference on Machine Learning and Cybernetics, vol. 6, pp. 3501–3505. IEEE (2007)Google Scholar