A hybrid network that feeds coarse log-signature features into an RNN is universal for SDE solution maps and beats baseline RNNs on action and gesture recognition benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning stochastic differential equations using RNN with log signature features
A hybrid network that feeds coarse log-signature features into an RNN is universal for SDE solution maps and beats baseline RNNs on action and gesture recognition benchmarks.