AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Neural Complexity Measures

Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi

NeurIPS 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Normalization and unsupervised meta-learning · 5 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
Regularize task learning with Neural Complexityimage classification learners · MNISTtest accuracyImproved
Regularize task learning with Neural Complexityimage classification learners · FMNISTtest accuracyImproved
Regularize task learning with Neural Complexityimage classification learners · KMNISTtest accuracyImproved
Regularize task learning with Neural Complexityimage classification learners · SVHNtest accuracyHurt
Regularize task learning with Neural Complexityimage classification learners · CIFAR-10test accuracyImproved
Regularize the learner with Neural Complexity rather than MetaRegsinusoid regression · Sinusoid regressiontest lossImproved
Use Huber loss instead of MSE to train Neural Complexity (ablation)Neural Complexity on Omniglot · Omniglot 10-way 1-shotaccuracyImproved
Add a bias term to the classification interaction layer (ablation)Neural Complexity classification architecture · Omniglot 10-way 1-shotaccuracyImproved
Include training loss in the classification interaction layer (ablation)Neural Complexity classification architecture · Omniglot 10-way 1-shotaccuracyImproved
Use the bilinear layer in the classification interaction (ablation)Neural Complexity classification architecture · Omniglot 10-way 1-shotaccuracyImproved
Transfer Neural Complexity regularization to a task learner with 4 layerssinusoid regression task learner · Sinusoid regression with changed learner hyperparameterstest lossHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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