Login / Signup
MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts.
Zhitian Xie
Yinger Zhang
Chenyi Zhuang
Qitao Shi
Zhining Liu
Jinjie Gu
Guannan Zhang
Published in:
CoRR (2024)
Keyphrases
</>
similarity measure
probabilistic model
computational model
high level
probability distribution
least squares
statistical model
autoregressive
knowledge base
closed form
experimental data
theoretical framework
domain experts
em algorithm
knowledge acquisition
graphical models
cost function
evolutionary algorithm