AI Paper Atlas

Research map / Optimization / Optimizers

Improved Dropout for Shallow and Deep Learning

Zhe Li, Boqing Gong, Tianbao Yang

NeurIPS 2016 · Optimization › Optimizers · approach: Natural gradient and Fisher approximations · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace standard Bernoulli dropout with evolutional dropout (mini-batch second-order sampling probabilities)CNN on CIFAR-100 · CIFAR-100testing performance: over 10% relative improvementImproved
replace standard dropout with evolutional dropoutCNN on CIFAR-100 · CIFAR-100convergence speed: over 50%Improved
replace standard dropout with data-dependent dropoutlogistic regression · real-sim, news20, RCV1training/testing error convergenceImproved
replace standard dropout with evolutional dropoutCNNs on MNIST, SVHN, CIFAR-10, CIFAR-100 · MNIST, SVHN, CIFAR-10, CIFAR-100convergence speedImproved
run SVHN training beyond 12000 iterationsevolutional vs standard dropout · SVHNerror curvesNo clear effect
evolutional dropout instead of BN plus standard dropoutCaffe CIFAR-10 network · CIFAR-10testing accuracyNo clear effect
use sigmoid activation with BN instead of ReLU (ablation)BN network · CIFAR-10testing accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy