Application of Genetic Algorithms in Machine learning
暂无分享,去创建一个
This Genetic Algorithms (GAs) are a type of optimization algorithms which combine survival of the fittest and a simplified version of Genetic Process .It has as yet not been proved whether machine learning can be considered as a problem apt for applying GAs. Therefore the work explores the use of GAs in Machine learning. A detailed study on the success of GAs in machine learning was carried out by R. D. King, R. Henery, C. Feng, and A. Sutherland [4] but it was limited to comparison. The paper takes the example of Chess to apply GA and proposes a new technique to apply GA to machine learning which can substitute the existing methodologies .The work proposed is shown to be robust and thus making the learning a natural process rather than an algorithmic one. The paper relies on the randomness of GAs and their ability to make the population converge towards the desired point using a fitness function and combines it with the concept of feedback similar to that of neural networks. Keywords— Genetic Algorithm, Machine learning, Classifier, Supervised learning.
[1] Arthur L. Samuel,et al. Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..
[2] Sebastian Thrun,et al. Learning to Play the Game of Chess , 1994, NIPS.
[3] Gabriella Kókai,et al. GeLog - A System Combining Genetic Algorithm with Inductive Logic Programming , 2001, Fuzzy Days.
[4] Cao Feng,et al. A Comparative Study of Classification Algorithms: Statistical, Machine Learning and Neural Network , 1992, Machine Intelligence 13.