Login / Signup

Transformers learn in-context by gradient descent.

Johannes von OswaldEyvind NiklassonEttore RandazzoJoão SacramentoAlexander MordvintsevAndrey ZhmoginovMax Vladymyrov
Published in: CoRR (2022)
Keyphrases
  • contextual information
  • objective function
  • cost function
  • context sensitive
  • context dependent
  • real time
  • databases
  • artificial intelligence
  • metadata
  • multimedia
  • decision trees
  • hidden markov models
  • context awareness