Lecture presented by Lucas Ondel (LISN).
This lecture will cover how to use finite state methods to train and conduct inference with neural networks. We will explore how finite state methods can be used to define standard loss functions for sequence-to-sequence training, how to back-propagate the gradient through finite state automata and how one can leverage GPU to accelerate inference in large automata.
Mots clés : finite state methods ia informatique jsalt neural networks workshop
Informations
- Gregor Dupuy
- 5 juillet 2023 07:16
- Conférence
- Anglais
- Master