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 “4 Training the Network” · whole deck
4 Training the Network
- What objective is a CTC network trained with?Maximum likelihood: minimize \(O^{ML} = -\sum_{(\mathbf{x}, \mathbf{z}) \in S} \ln p(\mathbf{z} \mid \mathbf{x})\), the same principle as standard network objectives. Its derivatives with respect to the outputs are backpropagated through time.
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §4, p. 372
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