A mixture of experts committee machine to design compensators for intensity modulated radiation therapy

Authors:
J. H. Goodband;O. C. L. Haas;J. A. Mills
Affiliations:
Control Theory and Applications Centre, Coventry University, Priory St, Coventry, CV1 5FB, UK;Control Theory and Applications Centre, Coventry University, Priory St, Coventry, CV1 5FB, UK;University Hospitals Coventry and Warwickshire NHS Trust, (Walsgrave Hospital), Clifford Bridge Road, Coventry, CV2 4ED, UK
Venue:
Pattern Recognition
Year:
2006

Citing 8
Cited 3

Connectionist learning procedures

Artificial Intelligence
The Strength of Weak Learnability

Machine Learning
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Practical neural network recipes in C++

Practical neural network recipes in C++
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Convergence Properties of the Nelder--Mead Simplex Method in Low Dimensions

SIAM Journal on Optimization
A Bayesian Committee Machine

Neural Computation

Teacher-directed learning in view-independent face recognition with mixture of experts using overlapping eigenspaces

Computer Vision and Image Understanding
Application of mixture of experts to construct real estate appraisal models

HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
Investigation of mixture of experts applied to residential premises valuation

ACIIDS'13 Proceedings of the 5th Asian conference on Intelligent Information and Database Systems - Volume Part II

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a new algorithm to produce a near optimal mixture of experts model (MEM) architecture for a continuous mapping. The MEM is applied to a new method incorporating photon scatter for designing compensators for intensity modulated radiation therapy. The algorithm utilizes the fuzzy C-means clustering algorithm to partition data before training commences. A reduction in the size of training sets also allows the Levenberg-Marquardt algorithm to be implemented. As a result, both training time and validation error are reduced. A 71% reduction in prediction error compared with that of a single neural network is achieved.