Authors:
Weiwei Yu
1
;
Kurosh Madani
2
and
Christophe Sabourin
2
Affiliations:
1
Northwestern Polytechnical University, China
;
2
UPEC University and Senart-Fontainebleau Institute of Technology, France
Keyword(s):
CMAC neural network, Structural parameters, Q-learning, Structure optimization.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Health Engineering and Technology Applications
;
Higher Level Artificial Neural Network Based Intelligent Systems
;
Human-Computer Interaction
;
Learning Paradigms and Algorithms
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Supervised and Unsupervised Learning
;
Theory and Methods
Abstract:
Comparing with other neural networks based models, CMAC is successfully applied on many nonlinear control systems because of its computational speed and learning ability. However, for high-dimensional input cases in real application, we often have to make our choice between learning accuracy and memory size. This paper discusses how both the number of layer and step quantization influence the approximation quality of CMAC. By experimental enquiry, it is shown that it is possible to decrease the memory size without losing the approximation quality by selecting the adaptive structural parameters. Based on Q-learning approach, the CMAC structural parameters can be optimized automatically without increasing the complexity of its structure. The choice of this optimized CMAC structure can achieve a tradeoff between the learning accuracy and finite memory size. At last, the application of this Q-learning based CMAC structure optimization approach on the joint angle tracking problem for bipe
d robot is presented.
(More)