How to Train the Teacher Model for Effective Knowledge Distillation.
Shayan Mohajer HamidiXizhen DengRenhao TanLinfeng YeAhmed H. SalamahPublished in: CoRR (2024)
Keyphrases
- computational model
- formal model
- theoretical framework
- data sets
- additional knowledge
- cost function
- domain knowledge
- probability distribution
- conceptual framework
- theoretical analysis
- semantic models
- evaluation model
- statistical model
- process model
- knowledge discovery
- knowledge representation
- prior knowledge
- decision trees
- neural network