Abstract
In this paper feed-forward neural networks are introduced where hidden units employ orthogonal Hermite polynomials for their activation functions. The proposed neural networks have some interesting properties: (i) the basis functions are invariant under the Fourier transform, subject only to a change of scale, and (ii) the basis functions are the eigenstates of the quantum harmonic oscillator, and stem from the solution of Schrödinger’s diffusion equation. The proposed neural networks demonstrate the particle-wave nature of information and can be used in nonparametric estimation. Possible applications of neural networks with Hermite basis functions include system modelling and image processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cohen-Tannoudji, C., Diu, D., Laloë, F.: Mécanique Quantique I, Hermann (1998)
Strauss, W.A.: Partial Differential Equations: An Introduction. J. Wiley, Chichester (1992)
Kosko, B.: Neural networks and fuzzy systems: A dynamical systems approach to machine intelligence. Prentice Hall, Englewood Cliffs (1992)
Ventura, D., Martinez, T.: Quantum Associative Memory. Information Sciences 24, 273–296 (2000)
Perus, M.: Multi-level Synergetic Computation in Brain. Nonlinear Phenomena in Complex Systems 4, 157–193 (2001)
Rigatos, G.G., Tzafestas, S.G.: Parallelization of a fuzzy control algorithm using quantum computation. IEEE Transactions on Fuzzy Systems 10, 451–460 (2002)
Rigatos, G.G., Tzafestas, S.G.: Fuzzy learning compatible with quantum mechanics postulates. In: Computational Intelligence and Natural Computation, CINC 2003, North Carolina (2003)
Refregier, A.: Shapelets - I. A method for image analysis. Mon. Not. R. Astron. Soc. 338, 35–47 (2003)
Haykin, S.: Neural Networks: A Comprehensive Foundation. McMillan (1994)
Ma, L., Khorasani, K.K.: Constructive Feedforward Neural Networks Using Hermite Polynomial Activation Functions. IEEE Transactions on Neural Networks 16, 821–833 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rigatos, G.G., Tzafestas, S.G. (2006). Feed-Forward Neural Networks Using Hermite Polynomial Activation Functions. In: Antoniou, G., Potamias, G., Spyropoulos, C., Plexousakis, D. (eds) Advances in Artificial Intelligence. SETN 2006. Lecture Notes in Computer Science(), vol 3955. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11752912_33
Download citation
DOI: https://doi.org/10.1007/11752912_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34117-8
Online ISBN: 978-3-540-34118-5
eBook Packages: Computer ScienceComputer Science (R0)