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 “2.1 Label Error Rate” · whole deck
2.1 Label Error Rate
- What is the label error rate (LER)?The total edit distance (insertions, substitutions, deletions) between the classifier’s outputs and the targets on a test set, divided by the total number of target labels: \(\text{LER}(h, S') = \frac{1}{Z} \sum_{(\mathbf{x}, \mathbf{z}) \in S'} \text{ED}(h(\mathbf{x}), \mathbf{z})\).
- Graves et al., 2006, Connectionist Temporal Classification (Proceedings of the 23rd International Conference on Machine Learning (ICML 2006)), §2.1, 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