Using logsignatures as features or layers in a recurrent neural network
This code is for paper Learning stochastic differential equations using RNN with log signature features by Hao, Shujian, Terry, Weixin 2019
-
sde_learning
: Codes for synthetic SDE data learning -
Pen-digit_learning
: Codes for Pen-digit data learning -
gesture_learning
: Codes for Chalearn 2013 gesture data learning -
action_learning
: Codes for NTURGB+D 120 learning
Python 3.7 was used. The following external packages were used, and may be installed via pip3 install -r requirements.txt
.
iisignature==0.23
for calculating signatures. It is CPU-only; consequently signature-based models are currently bottlenecked here.