Research map / Architectures and efficiency / RNNs and normalization
Universal Approximation of Input-Output Maps by Temporal Convolutional Nets
Joshua Hanson, Maxim Raginsky
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 a ReLU TCN with context length set by the map's approximately finite memory | Causal, time-invariant input-output maps with approximately finite memory and continuous finite-window functionals · Uniform approximation on bounded input sequences | approximation error: < ε | Improved |
| Assume uniform asymptotic incremental stability, Lipschitz input/output maps, bounded reachable states, and summable stability decay | Recurrent state-space systems · Approximately finite memory | truncation error | Improved |
| Use a Demidovich stability criterion instead of requiring contractivity in the ordinary norm | Recurrent state-space systems · TCN approximation of recurrent-system input-output maps | approximation capability | Improved |
Closest papers by meaning
- On the approximation properties of recurrent encoder-decoder architectures (ICLR 2022 · similarity 0.88)
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers (NeurIPS 2021 · similarity 0.87)
- Inverse Approximation Theory for Nonlinear Recurrent Neural Networks (ICLR 2024 · similarity 0.86)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.86)
- Exploring the Promise and Limits of Real-Time Recurrent Learning (ICLR 2024 · similarity 0.86)
- Recurrent neural network dynamical systems for biological vision (NeurIPS 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.
