Research map / Architectures and efficiency / RNNs and normalization
Recurrently Controlled Recurrent 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 |
|---|---|---|---|
| replace a BiLSTM encoder with RCRN (ablation) | classification models · Amazon Reviews (16 datasets, macro average) | accuracy: +2.9% | Helped |
| replace a 3L-BiLSTM encoder with RCRN (ablation) | classification models · Amazon Reviews (16 datasets, macro average) | accuracy: +1.1% | Helped |
| replace a BiLSTM encoder with RCRN (ablation) | sentiment classification · IMDb | accuracy: +1.9% | Helped |
| replace a 3L-BiLSTM encoder with RCRN (ablation) | sentiment classification · IMDb | accuracy: +1% | Helped |
| replace the 3L-BiGRU encoder with GRU-based RCRN (ablation) | R-NET · NarrativeQA | BLEU-1: 38.1 vs 34.9 | Helped |
| replace stacked recurrent layers with a controller-listener recurrent encoder | sequence encoders · 26 NLP datasets | task score | Helped |
| add CUDA-level optimization to RCRN (ablation) | RCRN · IMDb runtime benchmark, sequence lengths 16, 32, 64, 128, 256 | training time: 19, 29, 53, 101, 219 -> 10, 13, 21, 40, 78 | Helped |
Closest papers by meaning
- Quasi-Recurrent Neural Networks (ICLR 2017 · similarity 0.88)
- Focused Hierarchical RNNs for Conditional Sequence Processing (ICML 2018 · similarity 0.88)
- Parallelizing Linear Recurrent Neural Nets Over Sequence Length (ICLR 2018 · similarity 0.88)
- Improving Bilinear RNN with Closed-loop Control (NeurIPS 2025 · similarity 0.86)
- A Tensor Decomposition Perspective on Second-order RNNs (ICML 2024 · similarity 0.86)
- Exploring the Promise and Limits of Real-Time Recurrent Learning (ICLR 2024 · similarity 0.86)
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.