Image approximation and smoothing by support vector regression

Chow, David; Lee, Tong

doi:10.1109/ijcnn.2001.938747

Cited by 13 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This leads to a unified expression of BSC when all functional Causes are modeled as GMMs. Chow and Lee [ 12 ] showed that GMM can highly compress the energy of grid-form data. This infers a simpler topology of BSC by comparing with those of vectoral Causes In addition; continuous Cause avoids the description length selection problem as no quantization is involved.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Signal Classifier

Chow

Yuen

2007

2007 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian Signal Classifier

Chow

Yuen

2007

2007 International Joint Conference on Neural Networks

View full text Add to dashboard Cite

show abstract

“…In this section, we repeat the experiment at the Ref. [3] by replacing SVM with ASRN to determine the weights. The target 256 x 256 image in this experiment is shown at fig.…”

Section: Regression Of 2d Sine Functionmentioning

confidence: 99%

“…The third layer perfomis a linear transformation from the hidden-unit space to the output space. It has been applied successfully in a nuniber of applications including image processing [3], speech recognition [6, 1, 91, time series analysis and adaptive equalization [7,4].…”

Section: Introductionmentioning

confidence: 99%

Agent swarm regression network ASRN

Chow

Tsui

2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)

View full text Add to dashboard Cite

A multi-agent system (MAS), with independent sofhvare agents interacting with each other to achieve common goals will complete concurrent distributed rash under atitononiotis control. In this paper, novel .RBF ASRN" is proposed and will be trained by a MAS . Each neuron of the ASRN is considered as an agent. which consists of per-defined simple agent behavior set. Afrer a suffirient number of iterations, rhe weights of iieurons can be determined. Two sets of experiment will be examincd to observe the effectiveness of the proposed method. Regression Network -"'Agent Swarm Regression Nehvork

show abstract