Abstract
In this research paper, the concept of hyper-spherical/hyper-ellipsoidal separability is introduced. Method of arriving at the optimal hypersphere (maximizing margin) separating two classes is discussed. By projecting the quantized patterns into higher dimensional space (as in encoders of error correcting code), the patterns are made hyper-spherically separable. Single/multiple layers of spherical/ellipsoidal neurons are proposed for multi-class classification. An associative memory based on hyper-ellipsoidal neuron is proposed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Rama Murthy, G.: Hybrid neural networks. In: Proceedings of International Conference of Power System Analysis, Control and Optimization (2008)
Bruck, J., Blaum, M.: Neural networks, error correcting codes and polynomials over the binary cube. IEEE Trans. Inf. Theory 35(5), 976–987 (1989)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. U.S.A. 79, 2554–2558 (1982)
Jankowski, S., Lozowski, A., Zureda, J.: Complex-valued multi-state neural associative memory. IEEE Trans. Neural Netw. 7, 1491–1496 (1996)
Hou, Z.G., Song, K.Y., Gupta, M.M., Tan, M.: Neural units with higher-order synaptic operations for robotic image processing applications. Soft Comput.-A Fusion Found. Methodol. Appl. 11(3), 221–228 (2007)
Gács, P., Lovász, L.: Khachiyans algorithm for linear programming. In: König, H., Korte, B., Ritter, K. (eds.) Mathematical Programming at Oberwolfach, pp. 61–68. Springer, Heidelberg (1981)
Rama Murthy, G.: Multidimensional Neural Networks: Unified Theory. New Age International (2008)
Rama Murthy, G.: Model, Novel Ceiling Neuronal: Artificial Neural Networks. IIIT Technical reports # IIIT/TR/2015/59
Rama Murthy, G.: NP Hard Problems: Multi-linear objective optimization problem (manuscript in preparation)
Raju, S., Rama Murthy, G., Jha, A., Anil, R.: Dynamics of ordinary and recurrent hopfield networks: novel themes. Accepted for IEEE IACC-2017, January 2017
Rama Murthy, G., Anil, R., Dileep, M.: Dynamics of structured complex recurrent hopfield networks. In: Proceedings of International Joint Conference on Neural Networks (IJCNN 2016), Vancouver, Canada, July 2016
Rama Murthy, G., Munugoti, S.D., Rayala, A.: Convolutional associative memory: FIR filter model of synapse. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9491, pp. 356–364. Springer, Cham (2015). doi:10.1007/978-3-319-26555-1_40
Rama Murthy, G., Gabbouj, M.: Existence and synthesis of complex hopfield type associative memories. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2015. LNCS, vol. 9095, pp. 356–369. Springer, Cham (2015). doi:10.1007/978-3-319-19222-2_30
Rama Murthy, G., Gabbouj, M.: On the design of hopfield neural networks: synthesis of hopfield type associative memories. In: Proceedings of IEEE International Joint Conference of Neural Networks (IJCNN 2015), July 2015
Rama Murthy, G., Kicanoglu, B., Gabbouj, M.: On the dynamics of a recurrent hopfield network. In: Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN 2015), July 2015
Rama Murthy, G., Gabbouj, M.: Linear congruential sequences: feedback and recurrent neural networks. In: Shetty, N.R., Prasad, N.H., Nalini, N. (eds.) Emerging Research in Computing, Information, Communication and Applications, pp. 213–222. Springer, New Delhi (2015). doi:10.1007/978-81-322-2550-8_20
Rama Murthy, G., Zolnierek, A., Koszalka, L.: Optimal control, of time varying linear systems: neural networks. In: 2014 International Symposium on Computational and Business Intelligence (ISCBI 2014), New Delhi, India, 6–7 December 2014
Rama Murthy, G.: Optimization of quadratic forms: NP hard problems: neural networks. In: 2013 International Symposium on Computational and Business Intelligence (ISCBI 2013), New Delhi, India, 24–26 August 2013
Rama Murthy, G.: Distributed signal processing: neural networks. In: IEEE Workshop on Computational Intelligence: Theories, Applications and Future Directions, IIT-Kanpur, 14 July 2013
Rama Murthy, G., Nischal, B.: Hopfield-amari neural network: minimization of quadratic forms. In: The 6th International Conference on Soft Computing and Intelligent Systems, Kobe Convention Center, Kobe, Japan, 20–24 November 2012
Rama Murthy, G.: Finite impulse response (FIR) filter model of synapses: associated neural networks. In: Proceedings of 4th International Conference on Natural Computation (ICNC 2008), October 2008
Rama Murthy, G.: A novel class of generative neural networks. In: Proceedings of 4th International Conference on Natural Computation (ICNC 2008), October 2008
Rama Murthy, G.: Hybrid neural networks. In: Proceedings of International Conference on Power System Analysis, Control and Optimization (PSACO 2008), 13–15 March 2008
Rama Murthy, G., Praveen, D.: A novel associative memory on the complex hypercubic lattice. In: Proceedings of 16th European Symposium on Artificial Neural Networks (2008)
Rama Murthy, G.: Optimal robust filter models of synapse : associated neural networks. In: Proceedings of International Conference on Soft Computing and Intelligent Systems, 27–29 December 2007
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
Garimella, R.M., Yaparla, G., Singh, R.P. (2017). Optimal Spherical Separability: Artificial 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_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-59153-7_29
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)