An Exact Reformulation of Feature-Vector-based Radial-Basis-Function Networks for Graph-based Observations

by   Isaac J. Sledge, et al.
University of Florida
U.S. Navy

Radial-basis-function networks are traditionally defined for sets of vector-based observations. In this short paper, we reformulate such networks so that they can be applied to adjacency-matrix representations of weighted, directed graphs that represent the relationships between object pairs. We re-state the sum-of-squares objective function so that it is purely dependent on entries from the adjacency matrix. From this objective function, we derive a gradient descent update for the network weights. We also derive a gradient update that simulates the repositioning of the radial basis prototypes and changes in the radial basis prototype parameters. An important property of our radial basis function networks is that they are guaranteed to yield the same responses as conventional radial-basis networks trained on a corresponding vector realization of the relationships encoded by the adjacency-matrix. Such a vector realization only needs to provably exist for this property to hold, which occurs whenever the relationships correspond to distances from some arbitrary metric applied to a latent set of vectors. We therefore completely avoid needing to actually construct vectorial realizations via multi-dimensional scaling, which ensures that the underlying relationships are totally preserved.



There are no comments yet.


page 8

page 9

page 15


Online Learning with Radial Basis Function Networks

We investigate the benefits of feature selection, nonlinear modelling an...

Radial basis function process neural network training based on generalized frechet distance and GA-SA hybrid strategy

For learning problem of Radial Basis Function Process Neural Network (RB...

Nearest Neighbour Radial Basis Function Solvers for Deep Neural Networks

We present a radial basis function solver for convolutional neural netwo...

Nonlinear Matrix Approximation with Radial Basis Function Components

We introduce and investigate matrix approximation by decomposition into ...

Stability estimates for radial basis function methods applied to time-dependent hyperbolic PDEs

We derive stability estimates for three commonly used radial basis funct...

Meshless Approximation and Helmholtz-Hodge Decomposition of Vector Fields

The analysis of vector fields is crucial for the understanding of severa...

Rotation Invariant Face Detection Using Wavelet, PCA and Radial Basis Function Networks

This paper introduces a novel method for human face detection with its o...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.