Skip to main content
. Author manuscript; available in PMC: 2018 Jan 26.
Published in final edited form as: Adv Neural Inf Process Syst. 2017 Dec;30:3239–3249.

Table 4.

A simple study of the effect of adding a transformation regularization (TR) term to the objective function, evaluated on a labeled validation set. We see that adding the term improves performance for both heuristic (random) TF sequences and for TF sequences generated by the trained LSTM model, and that there is a larger positive effect for the latter.

Task % Augmentation Model TR Term Coefficient Accuracy (Dev.)
CIFAR-10 10 Heuristic 0 77.4
Heuristic 0.1 77.5
LSTM 0 80.4
LSTM 0.1 81.6