Combining Regression Trees and Radial Basis Function Networks

Abstract

We describe a method for non-parametric regression which combines regression trees with radial basis function networks. The method is similar to that of Kubat, who was first to suggest such a combination, but has some significant improvements. We demonstrate the features of the new method, compare its performance with other methods on DELVE data sets and apply it to a real world problem involving the classification of soybean plants from digital images.

Modeling and Analyzing the Effect of Microarchitecture Design Parameters on Microprocessor Soft Error Vulnerability

“…The output of a hidden unit is determined by the input-output transfer function that is specified for that unit. The commonly used transfer functions include sigmoid, linear threshold function, and Radial Basis Function (RBF) [17]. The ANN output, which is determined by the output unit, is computed using the responses of the hidden units and the weights between the hidden and output units.…”

“…The training of the RBF network involves selecting the center locations and radii, which are eventually used to determine the weights, using a regression tree [17]. A regression tree recursively partitions the input data set into subsets with decision criteria.…”

“…Each node contributes one unit to the RBF network's center and radius vectors. In our study, the selection of RBF centers is performed by recursively parsing regression tree nodes using a strategy proposed in [17].…”

Informed Microarchitecture Design Space Exploration Using Workload Dynamics

“…The output of a hidden unit is determined by the input-output transfer function that is specified for that unit. The commonly used transfer functions include sigmoid, linear threshold function and Radial Basis Function (RBF) [16]. The ANN output, which is determined by the output unit, is computed using the responses of the hidden units and the weights between the hidden and output units.…”

“…Each node contributes one unit to RBF network's center and radius vectors. In our study, the selection of RBF centers is performed by recursively parsing regression tree nodes using a strategy proposed in [16].…”