4 April 1997 Fast training analog approximator on the basis of Legendre polynomials
Author Affiliations +
In a number of applications the approximation, interpolation or nonlinear extrapolation of certain weakly (when every subsequent term of power series expansion is much less than previous one) nonlinear dependencies d(x), where x an arbitrary signal in time, is demanded. The problem of cancellation of nonlinear distortions of a signal in high precision analog engineering can be an example. In such cases it seems to be reasonable to use polynomial-based devices. In this paper the neural network based devices able to perform the operations of approximation, interpolation and nonlinear extrapolation are described. The schemes and working characteristics of a breadboard, based on analog radio components, are presented. Legendre polynomials were offered as basis functions for significant increasing of the speed of the approximator training. The scheme of analog synthesizer of Legendre polynomials was also suggested.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Vyacheslav N. Chesnokov, Vyacheslav N. Chesnokov, } "Fast training analog approximator on the basis of Legendre polynomials", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271501; https://doi.org/10.1117/12.271501


Optical Neural Networks
Proceedings of SPIE (February 07 1989)
Applications of smart neuromorphic focal planes
Proceedings of SPIE (October 31 1990)
Implementing neural nets on non-ideal analog hardware
Proceedings of SPIE (November 08 1993)

Back to Top