Advertisement

Quantum Based Learning with Binary Neural Network

  • Om Prakash Patel
  • Aruna Tiwari
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 32)

Abstract

In this paper, a quantum based binary neural network learning algorithm is proposed for solving two class problems. The proposed method constructively forms the neural network architecture and weights are decided by quantum computing concept. The use of quantum computing optimizes the network structure and the performance in terms of number of neurons at hidden layer and classification accuracy. This approach is compared with MTiling-real networks algorithm and it is found that there is a significant improvement in terms of number of neurons at the hidden layer, number of iterations, training accuracy and generalization accuracy.

Keywords

Quantum computing Qubit Binary neural network Qubit gates 

References

  1. 1.
    Simon, H.: Neural Networks and Learning Machines. Prentice Hall, Upper Saddle River (2008)Google Scholar
  2. 2.
    Lu, T.C., Yu, G.R., Juang, J.C.: Quantum-based algorithm for optimizing artificial neural networks. IEEE Trans. Neural Netw. Learn. Syst. 24, 1266–1278 (2013)CrossRefGoogle Scholar
  3. 3.
    Xu, Y., Chaudhari, N.: Application of binary neural networks for classification. In: 2003 International Conference on Machine Learning and Cybernetics, vol. 3, pp. 1343–1348. IEEE (2003)Google Scholar
  4. 4.
    Parekh, R., Yang, J., Honavar, V.: Constructive neural-network learning algorithms for pattern classification. IEEE Trans. Neural Netw. 11, 436–451 (2000)CrossRefGoogle Scholar
  5. 5.
    Han, K.H., Kim, J.H.: Quantum-inspired evolutionary algorithms with a new termination criterion, Hε gate, and two-phase scheme. IEEE Trans. Evol. Comput. 8, 156–169 (2004)CrossRefGoogle Scholar
  6. 6.
    Mori, K., Isokawa, T., Kouda, N., Matsui, N., Nishimura, H.: Qubit inspired neural network towards its practical applications. In: International Joint Conference on Neural Networks, 2006, IJCNN’06, pp. 224–229. IEEE (2006)Google Scholar
  7. 7.
    de Araujo, R.A., Aranildo, R., Ferreira, T.: A quantum-inspired intelligent hybrid method for stock market forecasting. In: IEEE World Congress on Computational Intelligence Evolutionary Computation, 2008, CEC 2008, pp. 1348–1355. IEEE (2008)Google Scholar
  8. 8.
    Wang, D., Chaudhari, N.S.: Binary neural network training algorithms based on linear sequential learning. Int. J. Neural Syst. 13, 333–351 (2003)CrossRefGoogle Scholar
  9. 9.
    Zhang, C., Yang, J., Wu, W.: Binary higher order neural networks for realizing boolean functions. IEEE Trans. Neural Netw. 22, 701–713 (2011)CrossRefGoogle Scholar
  10. 10.
    Blake, C., Merz, C.J.: {UCI} repository of machine learning databases. Department of Information and Computer Science, University of California Irvine, Irvine, CA (1998) [Online]. Available http://www.ics.uci.edu/mlearn/MLRepository.html

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology IndoreIndoreIndia

Personalised recommendations