Complexity reduction in radial basis function (RBF) networks by using radial B-spline functions

Date

1998-01-01

Author

Saranlı, Afşar
Baykal, Buyurman

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

43
views

0
downloads

In this paper, new basis consisting of radial cubic and quadratic B-spline functions are introduced together with the CORDIC algorithm, within the context of RBF networks as a means of reducing computational complexity in real-time signal-processing applications. The new basis are compared with two other existing and popularly used basis families, namely the Gaussian functions and the inverse multiquadratic functions (IVMQ) in terms of approximation performance and computational requirements. The new basis are shown to achieve approximation performance very similar to the Gaussian basis functions and are better than the IVMQ functions with less computational load and without any need for approximation methods such as table-lookup.

Subject Keywords

RBF, Computational Complexity, B-Splines, CORDIC

URI

https://hdl.handle.net/11511/42279

Journal

NEUROCOMPUTING

DOI

https://doi.org/10.1016/s0925-2312(97)00078-7

Collections

Department of Electrical and Electronics Engineering, Article

Suggestions

OpenMETU
Core

Fixed-frequency slice computation of discrete Cohen's bilinear class of time-frequency representations Ozgen, MT (2000-02-01) This communication derives DFT-sample-based discrete formulas directly in the spectral-correlation domain for computing fixed-frequency slices of discrete Cohen's class members with reduced computational cost, both for one-dimensional and multidimensional (specifically two-dimensional (2-D)) finite-extent sequence cases. Frequency domain integral expressions that define discrete representations are discretized to obtain these discrete implementation formulas. 2-D ambiguity function domain kernels are chosen...
Loop-based conic multivariate adaptive regression splines is a novel method for advanced construction of complex biological networks Ayyıldız Demirci, Ezgi; Purutçuoğlu Gazi, Vilda; Weber, Gerhard Wilhelm (2018-11-01) The Gaussian Graphical Model (GGM) and its Bayesian alternative, called, the Gaussian copula graphical model (GCGM) are two widely used approaches to construct the undirected networks of biological systems. They define the interactions between species by using the conditional dependencies of the multivariate normality assumption. However, when the system's dimension is high, the performance of the model becomes computationally demanding, and, particularly, the accuracy of GGM decreases when the observations...
Efficient performance computations for trellis-coded modulation Abou Rajab, H; Yucel, MD (1999-06-01) In this letter, the algorithm given by Rouanne and Costello for the computation of the distance spectrum is improved for trellis-coded modulation schemes having uncoded bits, i.e., for trellis diagrams having parallel paths, It is shown that, when through a trellis corresponding to such kind of codes, all parallel transitions (labeled by signal selectors) between states are considered as a single branch labeled by a subset, then defining subset selector distance polynomials makes the computational complexit...
Accurate multimode vibrational calculations using a B-spline basis: theory, tests and application to dioxirane and diazirinone Toffolı, Danıele; Sparta, Manuel; Christiansen, Ove (2011-01-01) The use of B-spline basis sets is explored in the context of a vibrational program for automatic potential energy surface (PES) construction and multimode anharmonic vibrational wave function calculation. Results are compared with calculations using localized Gaussians and harmonic oscillator basis functions. Potential energy surfaces are constructed in an iterative fashion using a recently developed adaptive density-guided approach. The basis set requirements for an accurate representation of the vibration...
ALGORITHMS FOR EFFICIENT VECTORIZATION OF REPEATED SPARSE POWER-SYSTEM NETWORK COMPUTATIONS AYKANAT, C; OZGU, O; Güven, Ali Nezih (1995-02-01) Standard sparsity-based algorithms used in power system applications need to be restructured for efficient vectorization due to the extremely short vectors processed, Further, intrinsic architectural features of vector computers such as chaining and sectioning should also be exploited for utmost performance, This paper presents novel data storage schemes and vectorization algorithms that resolve the recurrence problem, exploit chaining and minimize the number of indirect element selections in the repeated s...

Citation Formats

A. Saranlı and B. Baykal, “Complexity reduction in radial basis function (RBF) networks by using radial B-spline functions,” NEUROCOMPUTING, pp. 183–194, 1998, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/42279.