Optimizing the number of trees in a decision forest to discover a subforest with high ensemble accuracy using a genetic algorithm

Keyphrases

• Genetic Algorithm 100%
• Tree number 100%
• Ensemble Accuracy 100%
• Random Tree 100%
• Selection Strategy 50%
• Exhaustive Search 50%
• Decision Tree 25%
• Initial Population 25%
• Existing State 25%
• Decision Tree Ensemble 25%
• Logic Rules 25%
• UCI Machine Learning Repository 25%
• Decision Forest Algorithm 25%
• Ensemble Pruning 25%
• Greedy Algorithm 25%
• Computational Burden 25%
• Memory Overhead 25%
• Pruning Strategy 25%
• Comparable Accuracy 25%
• State-of-the-art Techniques 25%
• Large Memory 25%
• Single Decision Tree 25%
• Computational Overhead 25%
• Algorithm-based 25%
• Number of Candidates 25%

Computer Science

• Genetic Algorithm 100%
• Decision Tree 75%
• Exhaustive Search 50%
• Initial Population 25%
• Machine Learning 25%
• Learning System 25%