ACT lets RNNs dynamically adapt computation depth per input via a differentiable halting unit, yielding large gains on synthetic tasks and structural insights on language data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2016 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Adaptive Computation Time for Recurrent Neural Networks
ACT lets RNNs dynamically adapt computation depth per input via a differentiable halting unit, yielding large gains on synthetic tasks and structural insights on language data.