UPDF AI

Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

Alex Graves,Santiago Fernández,Faustino J. Gomez,Jürgen Schmidhuber

2006 · DOI: 10.1145/1143844.1143891
International Conference on Machine Learning · 4,974 Citations

TLDR

This paper presents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems of sequence learning and post-processing.