Information Technology Reference
In-Depth Information
fasten the training process. The resilient propagation algorithm in real and complex
domain are well tried by neural network community. The modification in existing
complex resilient propagation algorithm possesses reasonable logic which improves
its learning speedwithout increasing the complexity of algorithm. The wide spectrum
of benchmark and reallife examples presented in successive chapters confirm the
motivation of improved C RPROP. For a fair comparison, the computational costs
for optimization are measured in number of learning cycles [ 27 ]. The improved
complex resilient propagation ( C - i RPROP) can provide much faster convergence in
comparison to C BP and thus also smaller computational complexity.
References
1. Hirose, A.: Complex-Valued Neural Networks. Springer, New York (2006)
2. Nitta, T.: Orthogonality of decision boundaries in complex-valued neural networks. Neural
Comput. 16 (1), 73-97 (2004)
3. Aizenberg, I., Moraga, C.: Multilayer feedforward neural network based on multi-valued
neurons (MLMVN) and a back-propagation learning algorithm. Soft Comput. 11 (2), 169-
183 (2007)
4. Amin, M.F., Murase, K.: Single-layered complex-valued neural network for real-valued clas-
sification problems. Neurocomputing 72 (4-6), 945-955 (2009)
5. Savitha, R., Suresh, S., Sundararajan, N., Kim, H.J.: Fast learning fully complex-valued
classifiers for real-valued classification problems. In: Liu, D., et al. (eds.) ISNN 2011, Part I,
Lecture Notes in Computer Science (LNCS), vol. 6675, pp. 602-609 (2011)
6. Savitha, R., Suresh, S., Sundararajan, N., Kim, H.J.: A fully complex-valued radial basis
function classifier for real-valued classification. Neurocomputing 78 (1), 104-110 (2012)
7. Nitta, T.: An extension of the back-propagation algorithm to complex numbers. Neural Netw.
10 (8), 1391-1415 (1997)
8. Tripathi, B.K., Kalra, P.K.: Complex generalized-mean neuron model and its applications.
Appl. Soft Comput. (Elsevier Science) 11 (1), 768-777 (2011)
9. Nitta, T.: An analysis of the fundamental structure of complex-valued neurons. Neural Process.
Lett. 12 , 239-246 (2000)
10. Savitha, R., Suresh, S., Sundararajan, N., Saratchandran, P.: A new learning algorithm with
logarithmic performance index for complex- valued neural networks. Neurocomputing 72 (16-
18), 3771-3781 (2009)
11. Kim, T., Adali, T.: Approximation by fully complex multilayer perceptrons. Neural Comput.
15 , 1641-1666 (2003)
12. Savitha, R., Suresh, S., Sundararajan, N.: A fully complex-valued radial basis function network
and its learning algorithm. Int. J. Neural Syst. 19 (4), 253-267 (2009)
13. Amin, M.F., Islam, M.M., Murase, K.: Ensemble of single-layered complex-valued neural
networks for classification tasks. Neurocomputing 72 (10-12), 2227-2234 (2009)
14. Li, M.-B., Huang, G.-B., Saratchandran, P., Sundararajan, N.: Fully complex extreme learning
machine. Neurocomputing 68 , 306-314 (2005)
15. Brown, J.W., Churchill, R.V.: Complex Variables and Applications, VIIth edn. Mc Graw Hill,
New York (2003)
16. Saff, E.B., Snider, A.D.: Fundamentals of ComplexAnalysis withApplications to Engineering
and Science. Prentice Hall, Englewood Cliffs (2003)
17. Piazza, F., Benvenuto, N.: On the complex backpropagation algorithm. IEEE Trans. Sig. Proc.
40 (4), 967-969 (1992)
18. Tripathi, B.K., Kalra, P.K.: The novel aggregation function based neuron models in complex
domain. Soft Comput. (Springer) 14 (10), 1069-1081 (2010)
 
Search WWH ::




Custom Search