Comparative study of genetic programming vs. neural networks for the classification of buried objects
Charleston, SC（2009）
Abstract
A comparative study of neural networks and genetic programming was conducted on six character classification problems. Based on the obtained results of the six problems, genetic programming showed better performance than neural networks in the various levels of problem difficulty. Genetic programming also showed robustness to untrained data, which caused difficulties for the neural networks. The optimization of the neural network structure was observed to be integral in obtaining both convergence and acceptable performance. A clear trend for structure optimization is not evident in the case of neural networks, and a global optimal solution may not be practical. On the other hand, because of the global searching nature of genetic programming, these problems with neural networks could be solved by using genetic programming.
MoreTranslated text
Key words
buried object detection,genetic algorithms,image classification,neural nets,buried objects classification,character classification problems,genetic programming,neural network structure optimization,untrained data robustness,pixel,testing,training data,classification algorithms,neural network,artificial neural networks,feature extraction,neural networks,global optimization,artificial intelligence
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined