Function approximation on non-Euclidean spaces

Authors:
Pierre Courrieu
Affiliations:
Laboratoire de Psychologie Cognitive, CNRS-UMR 6146, Université de Provence, 29 avenue Robert Schuman, 13621 Aix-en-Provence cedex 1, France
Venue:
Neural Networks
Year:
2005

Citing 15
Cited 3

On the approximate realization of continuous mappings by neural networks

Neural Networks
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
The cascade-correlation learning architecture

Advances in neural information processing systems 2
Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem

Neural Networks
Original Contribution: A convergent generator of neural networks

Neural Networks
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Three algorithms for estimating the domain of validity of feedforward neural networks

Neural Networks
Some new results on neural network approximation

Neural Networks
A relaxation algorithm for estimating the domain of validity of feedforward neural networks

Neural Processing Letters
The String-to-String Correction Problem

Journal of the ACM (JACM)
An Extension of the String-to-String Correction Problem

Journal of the ACM (JACM)
Two methods for encoding clusters

Neural Networks
Interpolation by radial basis functions on Sobolev space

Journal of Approximation Theory
The Hyperbell Algorithm for Global Optimization: A Random Walk Using Cauchy Densities

Journal of Global Optimization
Straight monotonic embedding of data sets in Euclidean spaces

Neural Networks

Density codes and shape spaces

Neural Networks
The cooperative conceptualization of urban spaces in AI-assisted environmental planning

CDVE'09 Proceedings of the 6th international conference on Cooperative design, visualization, and engineering
Feature selection and multi-kernel learning for sparse representation on a manifold

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a family of layered feed-forward networks that is able to uniformly approximate functions on any metric space, and also on a wide variety of non-metric spaces. Non-Euclidean input spaces are frequently encountered in practice, while usual approximation schemes are guaranteed to work only on Euclidean metric spaces. Theoretical foundations are provided, as well as practical algorithms and illustrative examples. This tool potentially constitutes a significant extension of the common notion of 'universal approximation capability'.