Towards Understanding the Mixture-of-Experts Layer in Deep Learning.

Zixiang Chen Yihe Deng Yue Wu Quanquan Gu Yuanzhi Li

Published in: NeurIPS (2022)

Keyphrases

deep learning
restricted boltzmann machine
unsupervised learning
unsupervised feature learning
machine learning
mental models
pattern recognition
viewpoint
weakly supervised
data sets
information retrieval
multiscale
feature vectors
automatic extraction