Research map / Architectures and efficiency / RNNs and normalization
Time Adaptive Recurrent Neural Network
Check 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 |
|---|---|---|---|
| Use time-adaptive state updates with input-dependent time constants | RNN · Permute-MNIST | accuracy (%): 95.62 -> 97.13 | Helped |
| Use time-adaptive state updates with input-dependent time constants | RNN · Noisy-CIFAR | accuracy (%): 54.70 -> 59.06 | Helped |
| Use time-adaptive state updates with input-dependent time constants | RNN · PTB-300 | test perplexity: 113.38 -> 94.62 | Helped |
| Use time-adaptive state updates with input-dependent time constants | RNN · PTB character-level | BPC: 1.147 -> 1.19 | Hurt |
| Use time-adaptive state updates with input-dependent time constants | RNN · PTB word-level | perplexity: 51.1 -> 53.21 | Hurt |
| Use time-adaptive state updates with input-dependent time constants | RNN · NTU RGB-d cross-view | accuracy (%): 90.43 -> 90.86 | Helped |
| Use dense TARNN instead of 3-Layer TARNN (ablation) | TARNN · NTU RGB-d cross-subject | accuracy (%): 80.52 -> 82.31 | Helped |
| Use dense TARNN instead of 3-Layer TARNN (ablation) | TARNN · NTU RGB-d cross-view | accuracy (%): 87.54 -> 90.86 | Helped |
| Combine near-identity hidden-state gradients with selective skipping of uninformative inputs | TARNN · Toy sequence classification | accuracy: 60 -> 100% | Helped |
Closest papers by meaning
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.90)
- RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients? (ICLR 2020 · similarity 0.89)
- Training Recurrent Neural Networks Online by Learning Explicit State Variables (ICLR 2020 · similarity 0.88)
- Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies (NeurIPS 2023 · similarity 0.88)
- Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences (NeurIPS 2016 · similarity 0.88)
- Understanding and Controlling Memory in Recurrent Neural Networks (ICML 2019 · similarity 0.88)
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.