Journal
2014 14TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR)
Volume -, Issue -, Pages 279-284Publisher
IEEE
DOI: 10.1109/ICFHR.2014.54
Keywords
handwriting recognition; recurrent neural networks; GPU; batch-training
Ask authors/readers for more resources
In this paper we demonstrate a modified topology for long short-term memory recurrent neural networks that controls the shape of the squashing functions in gating units. We further propose an efficient training framework based on a mini-batch training on sequence level combined with a sequence chunking approach. The framework is evaluated on publicly available data sets containing English and French handwriting by utilizing a based implementation. Speedups of more than 3x are achieved in training recurrent neural network models which outperform state of the art recognition results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available