Search Results for author:
Found 2 papers, 1 papers with code
Guided Evolutionary Neural Architecture Search With Efficient Performance Estimation
GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialisation stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation.
Ranked #16 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-100
Guided Evolution for Neural Architecture Search
The rationale behind G-EA, is to explore the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring network is trained and kept for the next generation.
