Login / Signup
Transformer Dissection: An Unified Understanding for Transformer's Attention via the Lens of Kernel.
Yao-Hung Hubert Tsai
Shaojie Bai
Makoto Yamada
Louis-Philippe Morency
Ruslan Salakhutdinov
Published in:
CoRR (2019)
Keyphrases
</>
fuzzy logic
power transformers
fault diagnosis
power system
partial discharge
incipient fault
distribution network
high voltage
genetic algorithm
gaussian processes
data sets
artificial intelligence
clustering algorithm
multiscale
focus of attention
kernel space