Abstract
This paper presents the deduction of the quasi-Newton learning methods for training quaternion-valued feedforward neural networks, using the framework of the HR calculus. Since these algorithms yielded better training results than the gradient descent for the real- and complex-valued cases, an extension to the quaternion-valued case is a natural idea to enhance the performance of quaternion-valued neural networks. Experiments done on four time series prediction applications show a significant improvement over the quaternion gradient descent algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arena, P., Fortuna, L., Muscato, G., Xibilia, M.G.: Neural Networks in Multidimensional Domains Fundamentals and New Trends in Modelling and Control. Lecture Notes in Control and Information Sciences, vol. 234. Springer, London (1998)
Isokawa, T., Kusakabe, T., Matsui, N., Peper, F.: Quaternion neural network and its application. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, pp. 318–324. Springer, Heidelberg (2003). doi:10.1007/978-3-540-45226-3_44
Kusamichi, H., Isokawa, T., Matsui, N., Ogawa, Y., Maeda, K.: A new scheme for color night vision by quaternion neural network. In: International Conference on Autonomous Robots and Agents, pp. 101–106, December 2004
Buchholz, S., Le Bihan, N.: Polarized signal classification by complex and quaternionic multi-layer perceptrons. Int. J. Neural Syst. 18(2), 75–85 (2008)
Jahanchahi, C., Took, C., Mandic, D.: On HR calculus, quaternion valued stochastic gradient, and adaptive three dimensional wind forecasting. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–5. IEEE, July 2010
Took, C., Mandic, D., Aihara, K.: Quaternion-valued short term forecasting of wind profile. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE, July 2010
Took, C., Strbac, G., Aihara, K., Mandic, D.: Quaternion-valued short-term joint forecasting of three-dimensional wind and atmospheric parameters. Renew. Energy 36(6), 1754–1760 (2011)
Nocedal, J., Wright, S.: Numerical Optimization. Springer Series in Operations Research, Springer New York (1999)
Watrous, R.: Learning algorithms for connectionist networks: applied gradient methods of nonlinear optimization. Technical reports (CIS) MS-CIS-88-62, University of Pennsylvania, July 1988
Barnard, E.: Optimization for training neural nets. IEEE Trans. Neural Netw. 3(2), 232–240 (1992)
Popa, C.A.: Quasi-newton learning methods for complex-valued neural networks. In: International Joint Conference on Neural Networks (IJCNN). IEEE, July 2015
Xu, D., Xia, Y., Mandic, D.: Optimization in quaternion dynamic systems: gradient, Hessian, and learning algorithms. IEEE Trans. Neural Netw. Learn. Syst. 27(2), 249–261 (2016)
Luenberger, D., Ye, Y.: Linear and Nonlinear Programming. International Series in Operations Research & Management Science, vol. 116. Springer, Heidelberg (2008)
Fletcher, R., Powell, M.: A rapidly convergent descent method for minimization. Comput. J. 6(2), 163–168 (1963)
Shanno, D.: Conditioning of quasi-newton methods for function minimization. Math. Comput. 24(111), 647–656 (1970)
Battiti, R.: First and second-order methods for learning between steepest descent and Newton’s method. Neural Comput. 4(2), 141–166 (1992)
Mandic, D., Chambers, J.: Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability. Wiley, New York (2001)
Goh, S., Mandic, D.: A complex-valued RTRL algorithm for recurrent neural networks. Neural Comput. 16(12), 2699–2713 (2004)
Goh, S., Mandic, D.: Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN. IEEE Trans. Signal Process. 53(5), 1827–1836 (2005)
Goh, S., Mandic, D.: Stochastic gradient-adaptive complex-valued nonlinear neural adaptive filters with a gradient-adaptive step size. IEEE Trans. Neural Netw. 18(5), 1511–1516 (2007)
Goh, S., Mandic, D.: An augmented CRTRL for complex-valued recurrent neural networks. Neural Netw. 20(10), 1061–1066 (2007)
Xia, Y., Jelfs, B., Van Hulle, M., Principe, J., Mandic, D.: An augmented echo state network for nonlinear adaptive filtering of complex noncircular signals. IEEE Trans. Neural Netw. 22(1), 74–83 (2011)
Took, C., Mandic, D.: A quaternion widely linear adaptive filter. IEEE Trans. Signal Process. 58(8), 4427–4431 (2010)
Wang, M., Took, C., Mandic, D.: A class of fast quaternion valued variable stepsize stochastic gradient learning algorithms for vector sensor processes. In: International Joint Conference on Neural Networks (IJCNN), pp. 2783–2786. IEEE, August 2011
Ujang, C.B., Took, C., Mandic, D.: Quaternion-valued nonlinear adaptive filtering. IEEE Trans. Neural Netw. 22(8), 1193–1206 (2011)
Xia, Y., Jahanchahi, C., Mandic, D.: Quaternion-valued echo state networks. IEEE Trans. Neural Netw. Learn. Syst. 26(4), 663–673 (2015)
Buchholz, S., Sommer, G.: Quaternionic spinor MLP. In: European Symposium on Artificial Neural Networks, pp. 377–382, April 2000
Took, C., Mandic, D.: The quaternion lms algorithm for adaptive filtering of hypercomplex processes. IEEE Trans. Signal Process. 57(4), 1316–1327 (2009)
Took, C., Mandic, D., Benesty, J.: Study of the quaternion LMS and four-channel LMS algorithms. In: International Conference on Acoustics, Speech and Signal Processing, pp. 3109–3112. IEEE, April 2009
Che Ujang, B., Took, C., Mandic, D.: On quaternion analyticity: enabling quaternion-valued nonlinear adaptive filtering. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2117–2120. IEEE, March 2012
Arena, P., Baglio, S., Fortuna, L., Xibilia, M.: Chaotic time series prediction via quaternionic multilayer perceptrons. In: International Conference on Systems, Man and Cybernetics, vol. 2, pp. 1790–1794. IEEE (1995)
Arena, P., Fortuna, L., Muscato, G., Xibilia, M.: Multilayer perceptrons to approximate quaternion valued functions. Neural Netw. 10(2), 335–342 (1997)
Ujang, C.B., Took, C., Mandic, D.: Split quaternion nonlinear adaptive filtering. Neural Netw. 23(3), 426–434 (2010)
Took, C., Mandic, D.: Quaternion-valued stochastic gradient-based adaptive iir filtering. IEEE Trans. Signal Process. 58(7), 3895–3901 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Popa, CA. (2017). Quasi-Newton Learning Methods for Quaternion-Valued Neural Networks. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2017. Lecture Notes in Computer Science(), vol 10305. Springer, Cham. https://doi.org/10.1007/978-3-319-59153-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-59153-7_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59152-0
Online ISBN: 978-3-319-59153-7
eBook Packages: Computer ScienceComputer Science (R0)