FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding.

Sai Qian Zhang Bradley McDanel H. T. Kung

Published in: HPCA (2022)

Keyphrases

floating point
variable precision
training process
decision table
knowledge structures
rough sets
fixed point
reduction method
floating point arithmetic
instruction set
dominance relation
linear programming
decision trees
training set
set valued
decision rules
learning process
knowledge base
neural network