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.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
