https://xiaodu.io/ctc-explained/
References
- Graves et al., Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with RNNs. In ICML, 2006. (Graves提出CTC算法的原始论文)
- Graves et al., A Novel Connectionist System for Unconstrained Handwriting Recognition. In IEEE Transactions on PAML, 2009.(CTC算法在手写字识别中的应用)
- Graves et al., Towards End-to-End Recognition with RNNs. In JMLR, 2014.(CTC算法在端到端声学模型中的应用)
- Alex Graves, Supervised Sequence Labelling with Recurrent Neural Networks. In Studies in Computational Intelligence, Springer, 2012.( Graves 的博士论文,关于sequence learning的研究,主要是CTC)
本文介绍了CTC(连接时序分类)算法的基本原理及其在不同领域的应用案例,包括手写识别、声学模型等。CTC算法由Graves等人提出,为解决未分段序列数据的标注问题提供了一种有效的方法。
7768

被折叠的 条评论
为什么被折叠?



