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 “2 Temporal Classification” · whole deck
2 Temporal Classification
- Define temporal classification and how it differs from framewise classification.Temporal classification maps an input sequence \(\mathbf{x}\) of length \(T\) to a label sequence \(\mathbf{z}\) of length \(U \le T\), with no a priori alignment between them. Framewise classification labels each time step (frame) independently.
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §2, p. 370
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