AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Deep Learning in Target Space

Michael Fairbank, Spyridon Samothrakis, Luca Citi

JMLR 2022 · Architectures and efficiency › RNNs and normalization · approach: Neural-symbolic reasoning · 2 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
train in target space instead of weight spaceCNN · CIFAR-100 (no dropout)test accuracy (%): 40.3 -> 50.5Improved
train in target space instead of weight spaceCNN · CIFAR-10 (no dropout)test accuracy (%): 77.9 -> 82.6Improved
train in target space instead of weight spaceCNN · CIFAR-100 (dropout)test accuracy (%): 52.22 -> 60.4Improved
train in target space instead of weight spaceCNN · CIFAR-10 (dropout)test accuracy (%): 82.90 -> 87.4Improved
train in target space instead of weight spaceCNN · CIFAR-100 (dropout + ensemble)test accuracy (%): 56.85 -> 63.24Improved
train in target space instead of weight spaceCNN · MNIST (no dropout)test accuracy (%): 99.26 -> 99.29No clear effect
train in target space instead of weight space plus batch normalisationCNN · CIFAR-100 (no dropout)test accuracy (%): 46.5 -> 50.5Improved
train in target space instead of weight space plus batch normalisationCNN · MNIST-Fashion (dropout)test accuracy (%): 94.07 -> 93.7Hurt
train in target space instead of weight space plus batch normalisationCNN · MNIST (no dropout)test accuracy (%): 99.41 -> 99.29Hurt
add batch normalisation to weight spaceCNN · CIFAR-100 (no dropout)test accuracy (%): 40.3 -> 46.5Improved
add dropout to target space (ablation)CNN · CIFAR-100test accuracy (%): 50.5 -> 60.4Improved
add ensemble of two networks to target space with dropout (ablation)CNN · CIFAR-100test accuracy (%): 60.4 -> 63.24Improved

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