Publication Details
Title: Scatter-Partitioning RBF Network for Function Regression and Image Segmentation: Preliminary Results
Author: A. Baraldi
Group: ICSI Technical Reports
Date: June 1998
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1998/tr-98-017.pdf
Overview:
Scatter-partitioning Radial Basis Function (RBF) networks increase their number of degrees of freedom with the complexity of an input-output mapping to be estimated on the basis of a supervised training data set. Due to its superior expressive power a scatter-partitioning Gaussian RBF (GRBF) model, termed Supervised Growing Neural Gas (SGNG), is selected from the literature. SGNG employs a one-stage error-driven learning strategy and is capable of generating and removing both hidden units and synaptic connections. A slightly modified SGNG version is tested as a function estimator when the training surface to be fitted is an image, i.e., a 2-D signal whose size is finite. The relationship between the generation, by the learning system, of disjointed maps of hidden units and the presence, in the image, of pictorially homogeneous subsets (segments) is investigated. Unfortunately, the examined SGNG version performs poorly both as function estimator and image segmenter. This may be due to an intrinsic inadequacy of the one-stage error-driven learning strategy to adjust structural parameters and output weights simultaneously but consistently. In the framework of RBF networks, further studies should investigate the combination of two-stage error-driven learning strategies with synapse generation and removal criteria. Keywords: RBF networks, supervised and unsupervised learning from data, prototype vectors, synaptic links, Gestaltist theory, image segmentation, low-level vision
Bibliographic Information:
ICSI Technical Report TR-98-017
Bibliographic Reference:
A. Baraldi. Scatter-Partitioning RBF Network for Function Regression and Image Segmentation: Preliminary Results. ICSI Technical Report TR-98-017, June 1998
Author: A. Baraldi
Group: ICSI Technical Reports
Date: June 1998
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1998/tr-98-017.pdf
Overview:
Scatter-partitioning Radial Basis Function (RBF) networks increase their number of degrees of freedom with the complexity of an input-output mapping to be estimated on the basis of a supervised training data set. Due to its superior expressive power a scatter-partitioning Gaussian RBF (GRBF) model, termed Supervised Growing Neural Gas (SGNG), is selected from the literature. SGNG employs a one-stage error-driven learning strategy and is capable of generating and removing both hidden units and synaptic connections. A slightly modified SGNG version is tested as a function estimator when the training surface to be fitted is an image, i.e., a 2-D signal whose size is finite. The relationship between the generation, by the learning system, of disjointed maps of hidden units and the presence, in the image, of pictorially homogeneous subsets (segments) is investigated. Unfortunately, the examined SGNG version performs poorly both as function estimator and image segmenter. This may be due to an intrinsic inadequacy of the one-stage error-driven learning strategy to adjust structural parameters and output weights simultaneously but consistently. In the framework of RBF networks, further studies should investigate the combination of two-stage error-driven learning strategies with synapse generation and removal criteria. Keywords: RBF networks, supervised and unsupervised learning from data, prototype vectors, synaptic links, Gestaltist theory, image segmentation, low-level vision
Bibliographic Information:
ICSI Technical Report TR-98-017
Bibliographic Reference:
A. Baraldi. Scatter-Partitioning RBF Network for Function Regression and Image Segmentation: Preliminary Results. ICSI Technical Report TR-98-017, June 1998