Bayesian model selection for reducing bloat and overfitting in genetic programming for symbolic regression.
Geoffrey F. BomaritoPatrick E. LeserN. C. M. StraussK. M. GarbrechtJ. D. HochhalterPublished in: GECCO Companion (2022)
Keyphrases
- symbolic regression
- genetic programming
- bayesian model selection
- model selection
- posterior probability
- gene expression programming
- evolutionary computation
- cross validation
- fitness function
- data association
- grammatical evolution
- em algorithm
- regression problems
- parameter estimation
- evolutionary algorithm
- parameter optimization
- decision trees
- open source
- software package
- genetic algorithm
- probabilistic model
- active learning
- learning algorithm