Login / Signup

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer.

Jiing-Ping WangMing-Guang LinAn-Yeu Andy Wu
Published in: AICAS (2024)
Keyphrases
  • pairwise
  • fuzzy logic
  • real time
  • data sets
  • databases
  • artificial intelligence
  • social networks
  • reinforcement learning
  • data streams
  • cost effective