Login / Signup
MiniALBERT: Model Distillation via Parameter-Efficient Recursive Transformers.
Mohammadmahdi Nouriborji
Omid Rohanian
Samaneh Kouchaki
David A. Clifton
Published in:
CoRR (2022)
Keyphrases
</>
probabilistic model
computational model
objective function
high level
prior knowledge
theoretical analysis
experimental data
conceptual model
learning algorithm
decision making
maximum likelihood
em algorithm
kalman filter
bayesian framework
formal model
linear model