ConceptAlgorithm Self-Discovery
Algorithm Self-Discovery
A subfield of meta-learning in which optimization algorithms themselves become the objects of learning. Systems automatically search for and generate update rules more efficient than those designed by humans through interaction with the environment. A representative result in this area is Disco103.
Timeline (last 90 days)
Sep 30
Algorithm self-discovery is a branch of meta-learning that makes the optimization algorithm itself the object of learning, automatically searching for and generating update rules through interaction with the environment.
Unverified50%