Gene Editing Improves Genetic Programming for Symbolic Regression
A new arXiv preprint introduces GESR, a symbolic regression method that enhances Genetic Programming (GP) with gene editing. GP traditionally relies on random mutations and crossovers, which produce both beneficial and detrimental variations. GESR proposes a 'gene editing' mechanism to selectively apply mutations that are predicted to yield superior outcomes, acting as a metaphorical 'God' that guides evolution. The method aims to improve the efficiency and accuracy of discovering mathematical laws from scientific data. The paper is authored by researchers and posted on arXiv under ID 2605.10685.
Key facts
- GESR is a symbolic regression method based on Genetic Programming.
- It introduces gene editing to guide mutations and crossovers.
- Traditional GP uses entirely random genetic operations.
- The method aims to improve discovery of mathematical laws from data.
- The paper is available on arXiv with ID 2605.10685.
- Symbolic regression is a challenge in artificial intelligence.
- GP simulates evolution through genetic mutation and crossover.
- Gene editing in GESR acts as a 'God' foreseeing beneficial variations.
Entities
Institutions
- arXiv