TangoBERT: Reducing Inference Cost by using Cascaded Architecture.

Jonathan Mamou Oren Pereg Moshe Wasserblat Roy Schwartz

Published in: CoRR (2022)

Keyphrases

inference engine
real time
neural network
inference process
network architecture
cost reduction
probabilistic inference
cost sensitive
software architecture
bayesian networks
computer vision
response time
expert systems
total cost
dynamic bayesian networks
artificial intelligence
inference mechanism
database