Abstract
In this paper we continue the analysis of some structures with potentialities for Artificial Intelligence (AI) devices. We follow the suggestions of J.J. Hopfield about ensuring a sufficiently large number of equilibria which need to be asymptotically stable in some sense. Viewing AI devices as repetitive structures, we focus on those devices ensuring some stability properties of the equilibria from the design stage, pointing out that the so-called hyperstable blocks (in particular, the triplet connection) are suitable for this purpose. At the same time the possible number and localization of equilibria as well as their stability are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Danciu, D., Răsvan, V.: On structures with emergent computing properties. A connectionist versus control engineering approach. In: Rojas, I., Joya, G., Catala, A. (eds.) IWANN 2015. LNCS, vol. 9094, pp. 415–429. Springer, Cham (2015). doi:10.1007/978-3-319-19258-1_35
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. LNCS, vol. 7903, pp. 375–385. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38682-4_40
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.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)
Popov, V.M.: Hyperstability of Control Systems. Die Grundlehren der mathematischen Wissenschaften, vol. 204. Springer, Heidelberg (1973)
Neymark, Y.I.: Dynamical Systems and Controlled Processes (in Russian). Nauka, Moscow (1978)
Popov, V.M.: An analogue of electrical network synthesis in hyperstability (in Romanian). In: Proceedings of the Symposium on Analysis and Synthesis of Electrical Networks, no. III, p. 9.1. Power Institute of Romanian Academy (1967)
Vidyasagar, M.: Location and stability of the high-gain equilibria of nonlinear neural networks. IEEE Trans. Neural Netw. 4(4), 660–671 (1993)
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
Danciu, D., Răsvan, V. (2017). On Designing New Structures with Emergent Computing Properties. In: Cong, F., Leung, A., Wei, Q. (eds) Advances in Neural Networks - ISNN 2017. ISNN 2017. Lecture Notes in Computer Science(), vol 10261. Springer, Cham. https://doi.org/10.1007/978-3-319-59072-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-59072-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59071-4
Online ISBN: 978-3-319-59072-1
eBook Packages: Computer ScienceComputer Science (R0)