An inverse-regression model maps test accuracy distributions to layer sizes and suggests architectures that, in a small MLP study, beat the best accuracy in the original training grid.
Human-level control through deep rein- forcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
ASNN: Learning to Suggest Neural Architectures from Performance Distributions
An inverse-regression model maps test accuracy distributions to layer sizes and suggests architectures that, in a small MLP study, beat the best accuracy in the original training grid.