A Random Matrix Analysis of Learning with α-Dropout
2020
This article studies a one hidden layer neural network with generalized Dropout (α-Dropout), where the dropped out features are replaced with an arbitrary value α. Specifically, under a large dimensional data and network regime, we provide the generalization performances for this network on a binary classification problem. We notably demonstrate that a careful choice of α = 0 can drastically improve the generalization performances of the classifier.
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI