Pith. sign in

REVIEW 5 cited by

Maxout Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1302.4389 v4 pith:RLXFHEDX submitted 2013-02-18 stat.ML cs.LG

Ian J. Goodfellow , David Warde-Farley , Mehdi Mirza , Aaron Courville , Yoshua Bengio This is my paper · ORCID
classification stat.MLcs.LG
keywords dropoutmodelmaxoutapproximateaveragingbecausecalledtechnique
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Multiple-Identity Image Attacks Against Face-based Identity Verification

    cs.CV 2019-06 unverdicted novelty 6.0 of 10

    The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion re...

  2. Adaptive Regularization of Labels

    cs.LG 2019-08 conditional novelty 5.0 of 10

    Training a classifier with an auxiliary loss that matches its own non-ground-truth class probabilities to a learned per-class residual label improves accuracy on several benchmarks, though gains are small and top-5 Im...

  3. Biologically-inspired Salience Affected Artificial Neural Network (SANN)

    cs.NE 2019-08 conditional novelty 5.0 of 10

    SANN adds a per-node salience value to a small feedforward network; one salience-training pass after classification training raises sigmoid output confidence for the tagged image and its class on the animal silhouette set.

  4. Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning

    cs.LG 2019-07 unverdicted novelty 5.0 of 10

    Graph Laplacian interpolating activation replaces softmax in DNNs and improves natural accuracy, robust accuracy, and data efficiency.

  5. Machine Reading Comprehension: a Literature Review

    cs.CL 2019-06 unverdicted novelty 1.0 of 10

    A 2019 survey of machine reading comprehension corpora and methods.

Pith tools