Aprendizaje automático - In Codice Ratio: Machine Transcription in the Vatican Secret Archive (TF Dev Summit '19)

The "In Codice Ratio" research project is developing a machine transcription system to speed up large scale search and knowledge discovery from historical archives. A custom CNN trained on crowdsourced annotations enables the system to deal with challenging medieval handwriting. See the revamped dev site → https://www.tensorflow.org/ Watch all TensorFlow Dev Summit '19 sessions → http://bit.ly/TFDS19Sessions Event homepage → http://bit.ly/TFDS19 Subscribe to the TensorFlow YouTube channel → https://bit.ly/TensorFlow1 Speaker: Elena Nieddu, UniRoma Music by Terra Monk → http://bit.ly/TerraMonkTFDS Event Photo Album → http://bit.ly/TFSummit19 event: TensorFlow Dev Summit 2019; re_ty: Publish; product: TensorFlow - General;