Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks
Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006))
Subscriber deck — free during early access
1 cards in “5 Experiments” · whole deck
5 Experiments
- What network did Graves et al. use for CTC, and why?A bidirectional LSTM (BLSTM), combining LSTM’s ability to bridge long time lags with bidirectional access to past and future context; standard BRNNs and unidirectional networks did worse. The hybrid baseline used the same architecture, for a fair comparison.
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §5, p. 374
Source
- Alex Graves, Santiago Fernández, Faustino Gomez and Jürgen Schmidhuber. 2006. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks. In Proceedings of the 23rd International Conference on Machine Learning (ICML 2006), pp. 369–376. doi:10.1145/1143844.1143891