AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Adaptive Normalized Risk-Averting Training for Deep Neural Networks

Zhiguang Wang, Tim Oates, James Lo

AAAI 2016 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 6 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 MSE/CE training with ANRATConvNets · MNISTtest error %: 0.93 -> 0.52Improved
add dropout and ReLU to ANRAT ConvNets (ablation)ConvNets + ANRAT · MNISTtest error %: 0.52 -> 0.39Improved
replace CE/MSE training with ANRATConvNets + dropout · CIFAR-10accuracy %: 80.58 -> 85.15Improved
replace MSE with ANRATDeep MLP · MNISTtest error %: 1.91 -> 1.45Improved
replace CE with ANRATDeep MLP · MNISTtest error %: 2.4 -> 1.45Improved
replace MSE with ANRATShallow MLP · MNISTtest error %: 2.02 -> 1.94No clear effect
replace CE with ANRATShallow MLP · MNISTtest error %: 1.93 -> 1.94No clear effect
use ANRAT instead of unsupervised pretrainingDeep MLP · MNISTtest error %: 1.45 vs 1.41 and 1.2Hurt
replace MSE with ANRATDenoised auto-encoder · uniform vs Gaussian block masking noisereconstruction errorMixed

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