AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Meta Learning Backpropagation And Improving It

Louis Kirsch, Jürgen Schmidhuber

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired network comparison · 8 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
clone backprop in a deep (1 hidden layer) VSML RNN instead of a shallow oneVSML RNN · MNISTtest accuracy: 90\% -> 87\%Hurt
clone backprop in a deep (1 hidden layer) VSML RNN instead of a shallow oneVSML RNN · Fashion MNISTtest accuracy: 80\% -> 76\%Hurt
random input projection augmentation during meta training (ablation)VSML RNN · unseen datasetscumulative accuracyImproved
apply random projection augmentation to baselines (Meta RNN, Hebbian FW, FW memory) (ablation)Meta RNN baselines · unseen datasetscumulative accuracyNo clear effect
replace weights with shared tiny LSTMs (VSML) versus a Meta RNNmeta learner · Fashion MNIST (meta-test, unseen)cumulative accuracyImproved

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