Implementing Radial Basis Functions Using Bump-resistor Networks

Author

John G. Harris, Missouri University of Science and TechnologyFollow

Abstract

Radial Basis Function (RBF) networks provide a powerful learning architecture for neural networks [6]. We have implemented a RBF network in analog VLSI using the concept of bump-resistors. A bump-resistor is a nonlinear resistor whose conductance is a Gaussian-like function of the difference of two other voltages. The width of the Gaussian basis functions may be continuously varied so that the aggregate interpolating function varies from a nearest-neighbor lookup, piece-wise constant function to a globally smooth function. The bump-resistor methodology extends to arbitrary dimensions while still preserving the radiality of the basis functions. The feedforward network architecture needs no additional circuitry other than voltage sources and the ID bump-resistors.

Recommended Citation

J. G. Harris, "Implementing Radial Basis Functions Using Bump-resistor Networks," IEEE International Conference on Neural Networks Conference Proceedings, vol. 3, pp. 1894 - 1898, Institute of Electrical and Electronics Engineers, Dec 1994.

Department(s)

Electrical and Computer Engineering

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2025 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Dec 1994