Login / Signup

Large Models are Parsimonious Learners: Activation Sparsity in Trained Transformers.

Zonglin LiChong YouSrinadh BhojanapalliDaliang LiAnkit Singh RawatSashank J. ReddiKe YeFelix X. ChernFelix X. YuRuiqi GuoSanjiv Kumar
Published in: CoRR (2022)
Keyphrases
  • probabilistic model
  • neural network
  • learning process
  • learning experience
  • e learning
  • prior knowledge
  • model selection
  • learning activities
  • complex systems
  • statistical models
  • learner models
  • multi layered perceptron