Not really similar. Nutonian did straight-up genetic programming symbolic regres... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jmmcd on March 10, 2020 \| parent \| context \| favorite \| on: AutoML-Zero: Evolving machine learning algorithms ... Not really similar. Nutonian did straight-up genetic programming symbolic regression. This does genetic programming to discover ML algorithms.

lokimedes on March 11, 2020 [–]

Actually it is somewhat similar as both find the model, and obliviously fits the data to that model in the process. My use was finding a parameterization that could be reused through regular regression fitting.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact