RESN uses a training-free random-sampling error estimate to guide an evolutionary search over LSTM architectures, matching or beating several baselines at about half the optimization time.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Random Error Sampling-based Recurrent Neural Network Architecture Optimization
RESN uses a training-free random-sampling error estimate to guide an evolutionary search over LSTM architectures, matching or beating several baselines at about half the optimization time.