AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Deep Neural Nets with Interpolating Function as Output Activation

Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 25 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 the vanilla output activation with WNLLResNet50 · CIFAR100 test seterror rate: 25.09% -> 20.45%Improved
Replace the vanilla output activation with WNLLPreActResNet50 · CIFAR100 test seterror rate: 25.95% -> 21.51%Improved
Replace the vanilla output activation with WNLLVGG16 · CIFAR100 test seterror rate: 28.59% -> 25.72%Improved
Replace the vanilla output activation with WNLLResNet110 · SVHN test seterror rate: 2.55% -> 2.26%Improved
Replace the vanilla output activation with WNLLPreActResNet34 · SVHN test seterror rate: 3.66% -> 3.32%Improved
Use WNLL output activation instead of softmaxDeep neural nets trained with 1000 or 10000 CIFAR10 examples · CIFAR10 test setgeneralization error: up to 10 percentImproved
Use WNLL output activation instead of softmaxDeep neural nets trained with insufficient data · CIFAR10 test setgeneralization error across network depthMixed

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