Abstract
This paper starts by revisiting some founding, classical ideas for Neural Networks as Artificial Intelligence devices. The basic functionality of these devices is given by stability related properties such as the gradient-like and other collective qualitative behaviors. These properties can be linked to the structural – connectionist – approach. A version of this approach is offered by the hyperstability theory which is presented in brief (its essentials) in the paper. The hyperstability of an isolated Hopfield neuron and the interconnection of these neurons in hyperstable structures are discussed. It is shown that the so-called “triplet” of neurons has good stability properties with a non-symmetric weight matrix. This suggests new approaches in developing of Artificial Intelligence devices based on the triplet interconnection of elementary systems (neurons) in order to obtain new useful emergent collective computational properties.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Răsvan, V.: Reflections on neural networks as repetitive structures with several equilibria and stable behavior. In: Rojas, I., Joya, G., Cabestany, J. (eds.) IWANN 2013, Part II. LNCS, vol. 7903, pp. 375–385. Springer, Heidelberg (2013)
Graupe, D.: Principles of Artificial Neural Networks, Advanced Series on Circuits and Systems, vol. 6, 2nd edn. World Scientific, Singapore (2007)
Grossberg, S.: Self-organizing neural networks for stable control of autonomous behavior in a changing world. In: Taylor, J.G. (ed.) Mathematical Approaches to Neural Networks, pp. 139–197. Elsevier (1993)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 79(1), 2554–2558 (1982)
Hopfield, J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. USA 81(5), 3088–3092 (1984)
Neymark, Y.I.: Dynamical systems and controlled processes (in Russian). Nauka, Moscow (1978)
Danciu, D., Răsvan, V.: Dynamics of neural networks - some qualitative properties. In: Sandoval, F., Prieto, A.G., Cabestany, J., Graña, M. (eds.) IWANN 2007. LNCS, vol. 4507, pp. 8–15. Springer, Heidelberg (2007)
Danciu, D., Răsvan, V.: Gradient like behavior and high gain design of KWTA neural networks. In: Cabestany, J., Sandoval, F., Prieto, A., Corchado, J.M. (eds.) IWANN 2009, Part I. LNCS, vol. 5517, pp. 24–32. Springer, Heidelberg (2009)
Danciu, D.: Dynamics of neural networks as nonlinear systems with several equilibria. In: Porto, A.B., Pazos, A., Buno, W. (eds.) Advancing Artificial Intelligence Through Biological Process Applications, pp. 331–357. IGI Global Publisher (2009)
Danciu, D., Răsvan, V.: Systems with slope restricted nonlinearities and neural networks dynamics. In: Cabestany, J., Rojas, I., Joya, G. (eds.) IWANN 2011, Part II. LNCS, vol. 6692, pp. 565–572. Springer, Heidelberg (2011)
Danciu, D.: Systems with several equilibria. Applications to neural networks (in Romanian). Universitaria, Craiova Romania (2006)
Danciu, D.: Neural networks. Stability, synchronization, delays (in Romanian). Universitaria, Craiova Romania (2010)
Forti, M.: On global asymptotic stability of a class of nonlinear systems arising in neural network theory. J. Differ. Equ. 113(1), 246–264 (1994)
Forti, M., Tesi, A.: A new method to analyze complete stability of pwl Cellular Neural Networks. Int. J. Bifurcation Chaos 11(3), 655–676 (2001)
Marco, M.D., Forti, M., Grazzini, M., Pancioni, L.: Limit set dichotomy and convergence of cooperative piecewise linear neural networks. IEEE Trans. on Circuits and Systems I 58(5), 1052–1062, May 2011
Atencia, M., Joya, G., Sandoval, F.: Spurious minima and basins of attraction in higher-order Hopfield networks. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2686, pp. 350–357. Springer, Heidelberg (2003)
Qin, S., Xue, X.: Dynamical analysis of neural networks of subgradient systems. IEEE Trans. on Aut. Contr. 55(10), 2347–2352 (2010)
Lu, W., Wang, J.: Convergence analysis of a class of nonsmooth gradient systems. IEEE Trans. on Circuits and Systems I 55(11), 3514–3527, December 2008
Gelig, A.K., Leonov, G.A., Yakubovich, V.A.: Stability of systems with non-unique equilibria (in Russian). Nauka, Moscow (1978)
Leonov, G.A., Reitmann, V., Smirnova, V.B.: Non-Local Methods for Pendulum-Like Feedback Systems, Teubner-Texte zur Mathematik, vol. 132. B.G. Teubner Verlagsgeselllschaft, Stuttgart (1992)
Yakubovich, V.A., Leonov, G.A., Gelig, A.K.: Stability of Stationary Sets in Control Systems with Discontinuous Nonlinearities, Stability, Vibration and Control of Systems, Series A, vol. 14. World Scientific, Singapore (2004)
Halanay, A., Răsvan, V.: Applications of Liapunov Methods in Stability, Mathematics and its Applications, vol. 245. Kluwer Academic Publishers, Dordrecht (1993)
Răsvan, V.: Dynamical systems with several equilibria and natural Liapunov functions. Archivum Mathematicum 34(1), 207–215 (1998)
Brockett, R.W.: Dynamical systems that sort lists, diagonalize matrices and solve linear programming problems. In: Proc. IEEE Conference on Decision and Control, pp. 799–803. IEEE Press (1988)
Cohen, M.: The construction of arbitrary stable dynamics in nonlinear neural networks. Neural Networks 5, 83–103 (1992)
Warwick, K., Zhu, Q., Ma, Z.: A hyperstable neural network for the modelling and control of nonlinear systems. Sādhanā 25(2), 169–180 (2000)
Popov, V.M.: Hyperstability of Control Systems, Die Grundlehren der mathematischen Wissenschaften, vol. 204. Springer Verlag, Berlin (1973)
Popov, V.M.: An analogue of electrical network synthesis in hyperstability (in Romanian). In: Proc. Symposium on Analysis and Synthesis of Electrical Networks. p. 9.1. No. III, Power Institute of Romanian Academy (1967)
Kurosh, A.G.: Lectures in General Algebra. Pure and Applied Mathematics Monographs. Pergamon Press, London (1965)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Danciu, D., Răsvan, V. (2015). On Structures with Emergent Computing Properties. A Connectionist versus Control Engineering Approach. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2015. Lecture Notes in Computer Science(), vol 9094. Springer, Cham. https://doi.org/10.1007/978-3-319-19258-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-19258-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19257-4
Online ISBN: 978-3-319-19258-1
eBook Packages: Computer ScienceComputer Science (R0)