We present four training and prediction schedules from the same character-level recurrent neural network. The efficiency of these schedules is tested in terms of model effectiveness as a function of training time and amount of training data seen. We show that the choice of training and prediction schedule potentially has a considerable impact on the prediction effectiveness for a given training budget.
@article{arxiv.1605.02486,
title = {Efficiency Evaluation of Character-level RNN Training Schedules},
author = {Cedric De Boom and Sam Leroux and Steven Bohez and Pieter Simoens and Thomas Demeester and Bart Dhoedt},
journal= {arXiv preprint arXiv:1605.02486},
year = {2016}
}