Maxout Networks
This work improves classification accuracy for machine learning practitioners by introducing a novel model to enhance dropout, though it is incremental as it builds on existing dropout techniques.
The paper tackled the problem of designing models to leverage dropout for approximate model averaging, resulting in state-of-the-art classification performance on MNIST, CIFAR-10, CIFAR-100, and SVHN datasets.
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.