Machine Learning
Genetic Programming for Feature Discovery and Image Discrimination
Proceedings of the 5th International Conference on Genetic Algorithms
Complexity Compression and Evolution
Proceedings of the 6th International Conference on Genetic Algorithms
Towards Genetic Programming for Texture Classification
AI '01 Proceedings of the 14th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Open BEAGLE: A New C++ Evolutionary Computation Framework
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
An introduction to ROC analysis
Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Statistical Comparisons of Classifiers over Multiple Data Sets
The Journal of Machine Learning Research
The WEKA data mining software: an update
ACM SIGKDD Explorations Newsletter
A survey on the application of genetic programming to classification
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Drawing boundaries: using individual evolved class boundaries for binary classification problems
Proceedings of the 13th annual conference on Genetic and evolutionary computation
A bootstrapping approach to reduce over-fitting in genetic programming
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
| Hi-index | 0.00 |
This paper explores a range of class boundary determination techniques that can be used to improve performance of Genetic Programming (GP) on binary classification tasks. These techniques involve selecting an individualised boundary threshold in order to reduce implicit bias that may be introduced through employing arbitrarily chosen values. Individuals that can chose their own boundaries and the manner in which they are applied, are freed from having to learn to force their outputs into a particular range or polarity and can instead concentrate their efforts on seeking a problem solution. Our investigation suggests that while a particular boundary selection method may deliver better performance for a given problem, no single method performs best on all problems studied. We propose a new flexible combined technique which gives near optimal performance across each of the tasks undertaken. This method together with seven other techniques is tested on six benchmark binary classification data sets. Experimental results obtained suggest that the strategy can improve test fitness, produce smaller less complex individuals and reduce run times. Our approach is shown to deliver superior results when benchmarked against a standard GP system, and is very competitive when compared with a range of other machine learning algorithms.