Research map / Architectures and efficiency / RNNs and normalization
Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
Adam S. Charles, Dong Yin, Christopher J. Rozell
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 |
|---|---|---|---|
| use sparsity in canonical or Haar wavelet basis instead of DCT basis for inputs (ablation) | linear echo-state network recovery · Simulation, sparse inputs (L=40, N=100) | input recovery rMSE | Improved |
| use canonical or Haar right singular vectors instead of DCT for low-rank inputs (ablation) | linear echo-state network recovery · Simulation, low-rank inputs (L=40, N=100) | input recovery rMSE | Improved |
Closest papers by meaning
- Memory of recurrent networks: Do we compute it right? (JMLR 2024 · similarity 0.91)
- A Random Matrix Approach to Echo-State Neural Networks (ICML 2016 · similarity 0.90)
- Capacity and Trainability in Recurrent Neural Networks (ICLR 2017 · similarity 0.88)
- Improved memory in recurrent neural networks with sequential non-normal dynamics (ICLR 2020 · similarity 0.88)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.88)
- Frequency Domain Reservoir Computing (NeurIPS 2026 · similarity 0.87)
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.
