Kai Chen, Zhi-Jie Yan, Qiang Huo. A context-sensitive-chunk BPTT approach to training deep LSTM/BLSTM recurrent neural networks for offline handwriting recognition. In 13th International Conference on Document Analysis and Recognition, ICDAR 2015, Tunis, Tunisia, August 23-26, 2015. pages 411-415, IEEE, 2015. [doi]
Abstract is missing.