Research map / Architectures and efficiency / RNNs and normalization
Unitary Evolution Recurrent Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| unitary recurrent matrix (uRNN) instead of LSTM | RNN · Permuted pixel MNIST | test accuracy: 88 -> 91.4 | Helped |
| unitary recurrent matrix (uRNN) instead of LSTM | RNN · Pixel MNIST | test accuracy: 98.2 -> 95.1 | Hurt |
| uRNN instead of LSTM/tanh RNN | RNN · Copying memory T=100-500 | cross entropy | Helped |
| uRNN instead of LSTM | RNN · Adding problem | MSE | No clear effect |
Closest papers by meaning
- Eigenvalue Normalized Recurrent Neural Networks for Short Term Memory (AAAI 2020 · similarity 0.91)
- Learning Unitary Operators with Help From u(n) (AAAI 2017 · similarity 0.91)
- Full-Capacity Unitary Recurrent Neural Networks (NeurIPS 2016 · similarity 0.91)
- Learning Useful Representations of Recurrent Neural Network Weight Matrices (ICML 2024 · similarity 0.86)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.86)
- Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues (ICLR 2025 · 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.