Answers are grounded in this paper and cite their sources.
This paper describes the use of genetic programming to automatically synthesize the design for a fixed-length loaded symmetric dipole antenna whose gain at a specific wavelength exceeds that of a commercially-marketed human-designed antenna and that reaches the theoretical maximum value for an antenna of its type. The run of genetic programming started "from scratch" that is, without starting from a pre-existing human-created design; did not employ any knowledge base of human design techniques or principles from the field of antenna design; and did not benefit from any human intervention during the run. The run produced a human-competitive result.
No takes yet. Share an insight, caveat, or question.
Koza et al. (2007) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: