ML Anthology

Sequence Modeling with CTC

Awni Hannun
Distill 2017
doi:10.23915/distill.00008 /distill/2017/hannun2017distill-sequence/

Abstract

Distill articles are interactive publications and do not include traditional abstracts. This summary was written for the ML Anthology. Provides a visual guide to Connectionist Temporal Classification (CTC), an algorithm that enables neural networks to learn sequence-to-sequence mappings without aligned training data. Explains how CTC marginalizes over all possible alignments using dynamic programming.

Distill Code Semantic Scholar

Cite

Text

Hannun. "Sequence Modeling with CTC." Distill, 2017. doi:10.23915/distill.00008

Markdown

[Hannun. "Sequence Modeling with CTC." Distill, 2017.](https://mlanthology.org/distill/2017/hannun2017distill-sequence/) doi:10.23915/distill.00008

BibTeX

@article{hannun2017distill-sequence,
  title     = {{Sequence Modeling with CTC}},
  author    = {Hannun, Awni},
  journal   = {Distill},
  year      = {2017},
  doi       = {10.23915/distill.00008},
  url       = {https://mlanthology.org/distill/2017/hannun2017distill-sequence/}
}