Name
Abstract | ||
|---|---|---|
Early stopping typically stops training the first time validation fitness disimproves. This may not be the best strategy given that validation fitness can subsequently increase or decrease. We examine the effects of stopping subsequent to the first disimprovement in validation fitness, on symbolic regression problems. Stopping points are determined using criteria which measure generalisation loss and training progress. Results suggest that these criteria can improve the generalistion ability of symbolic regression functions evolved using Grammar-based GP. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1145/2001858.2001971 | GECCO (Companion) |
Keywords | Field | DocType |
symbolic regression function,generalistion ability,training progress,grammar-based gp,time validation fitness disimproves,genetic programming,best strategy,measure generalisation loss,validation fitness,symbolic regression problem,overfitting,grammatical evolution | Early stopping,Computer science,Generalization,Grammar,Genetic programming,Artificial intelligence,Overfitting,Grammatical evolution,Symbolic regression,Machine learning | Conference |
Citations | PageRank | References |
3 | 0.38 | 4 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Clíodhna Tuite | 1 | 12 | 1.09 |
| Alexandros Agapitos | 2 | 211 | 22.88 |
| Michael O'Neill | 3 | 876 | 69.58 |
| Anthony Brabazon | 4 | 918 | 98.60 |