Maxout Networks

Code

• github.com/mavenlin/cuda-convnet
  none★ 0
• github.com/paniabhisek/maxout
  pytorch★ 0
• github.com/minoring/nin-tf2
  tf★ 0
• github.com/pmallari/Emotion_Recognition_PyTorch
  pytorch★ 0
• github.com/pmallari/Emotion_Recognition
  tf★ 0
• github.com/philipperemy/tensorflow-maxout
  tf★ 0
• github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Maxout_Networks
  pytorch★ 0

Abstract

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.

Tasks

Benchmark Results

Reproductions