前言:
{
最近在github上更新了一些代码,但没在这里更新文章,这次就在这写一篇论文的阅读笔记。
论文是《Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural 'networks》(Alex Graves, Santiago Fernández,Faustino J. Gomez, Jürgen Schmidhuber,https://www.researchgate.net/publication/221346365_Connectionist_temporal_classification_Labelling_unsegmented_sequence_data_with_recurrent_neural_%27networks),主题是序列识别的方法。
}
正文:
{
首先,论文的第一节Introduction提到了之前方法的问题:
- they usually require a significant amount of task specific knowledge, e.g. to design the state models for HMMs, or choose the input features for CRFs; (2)they require explicit (and often questionable) dependency assumptions to make inference tractable, e.g. the assumption that observations are independent for HMMs; (3) for standard HMMs, training is generative, even though sequence labelling is discriminative.
(1)通常这些方法需要很多任务专属的知识,比如说需要为HMMs设计状态模型,