FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding.
Sai Qian ZhangBradley McDanelH. T. KungPublished in: CoRR (2021)
Keyphrases
- floating point
- variable precision
- training process
- decision table
- fixed point
- rough sets
- knowledge structures
- decision trees
- reduction method
- approximation algorithms
- instruction set
- floating point arithmetic
- linear programming
- set valued
- knowledge discovery
- pattern recognition
- data structure
- dominance relation
- artificial intelligence