Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Comparing fixed and adaptive computation time for recurrent neural networks

Autor
Fojo, D.; Campos, V.; Giro, X.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
6th International Conference on Learning Representations
Any de l'edició
2018
Data de presentació
2018-05-01
Llibre d'actes
Sixth International Conference on Learning Representations: Monday April 30-Thursday May 03, 2018, Vancouver Convention Center, Vancouver: [proceedings]
Pàgina inicial
1
Pàgina final
8
Projecte finançador
Computación de altas prestaciones VII
Procesado de señales multimodales y aprendizaje automático en grafos.
Repositori
http://hdl.handle.net/2117/118497 Obrir en finestra nova
URL
https://iclr.cc/Conferences/2018/Schedule?type=Workshop Obrir en finestra nova
Resum
Deep networks commonly perform better than shallow ones, but allocating the proper amount of computation for each particular input sample remains an open problem. This issue is particularly challenging in sequential tasks, where the required complexity may vary for different tokens in the input sequence. Adaptive Computation Time (ACT) was proposed as a method for dynamically adapting the computation at each step for Recurrent Neural Networks (RNN). ACT introduces two main modifications to the r...
Citació
Fojo, D., Campos, V., Giro, X. Comparing fixed and adaptive computation time for recurrent neural networks. A: International Conference on Learning Representations. "Sixth International Conference on Learning Representations: Monday April 30-Thursday May 03, 2018, Vancouver Convention Center, Vancouver: [proceedings]". 2018, p. 1-8.
Paraules clau
ACT, RNN, adaptive computation time, neural network, recurrent neural network, variable computation
Grup de recerca
GPI - Grup de Processament d'Imatge i Vídeo
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Fojo, Daniel  (autor ponent)
  • Campos Camúñez, Victor  (autor ponent)
  • Giro Nieto, Xavier  (autor ponent)

Arxius