Research map / Architectures and efficiency / RNNs and normalization
Meta Learning Backpropagation And Improving It
Louis Kirsch, Jürgen Schmidhuber
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 changed | Where | Measured | Effect |
|---|---|---|---|
| clone backprop in a deep (1 hidden layer) VSML RNN instead of a shallow one | VSML RNN · MNIST | test accuracy: 90\% -> 87\% | Hurt |
| clone backprop in a deep (1 hidden layer) VSML RNN instead of a shallow one | VSML RNN · Fashion MNIST | test accuracy: 80\% -> 76\% | Hurt |
| random input projection augmentation during meta training (ablation) | VSML RNN · unseen datasets | cumulative accuracy | Improved |
| apply random projection augmentation to baselines (Meta RNN, Hebbian FW, FW memory) (ablation) | Meta RNN baselines · unseen datasets | cumulative accuracy | No clear effect |
| replace weights with shared tiny LSTMs (VSML) versus a Meta RNN | meta learner · Fashion MNIST (meta-test, unseen) | cumulative accuracy | Improved |
Closest papers by meaning
- Meta-Learning in Neural Networks: A Survey (TPAMI 2021 · similarity 0.87)
- Meta-Learning with Neural Tangent Kernels (ICLR 2021 · similarity 0.87)
- Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm (ICLR 2018 · similarity 0.87)
- Learning To Learn by Jointly Optimizing Neural Architecture and Weights (CVPR 2022 · similarity 0.87)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · similarity 0.86)
- First-order ANIL provably learns representations despite overparametrisation (ICLR 2024 · similarity 0.85)
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.
