HyperAIHyperAI
2 months ago

Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections

Kim, Taewoon
Generalizing MLPs With Dropouts, Batch Normalization, and Skip
  Connections
Abstract

A multilayer perceptron (MLP) is typically made of multiple fully connectedlayers with nonlinear activation functions. There have been several approachesto make them better (e.g. faster convergence, better convergence limit, etc.).But the researches lack structured ways to test them. We test different MLParchitectures by carrying out the experiments on the age and gender datasets.We empirically show that by whitening inputs before every linear layer andadding skip connections, our proposed MLP architecture can result in betterperformance. Since the whitening process includes dropouts, it can also be usedto approximate Bayesian inference. We have open sourced our code, and releasedmodels and docker images at https://github.com/tae898/age-gender/

Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections | Latest Papers | HyperAI