Home Page

Papers

Submissions

News

Scope

Editorial Board

Announcements

Proceedings

Open Source Software

Search

Login



RSS Feed

Maxout Networks

Ian Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, Yoshua Bengio
;
JMLR W&CP 28 (3) : 1319–1327, 2013

Abstract

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We dene 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 dropouts 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 classication performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.

Related Material