Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
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 |
|---|---|---|---|
| Transform discrete-time PLRNN into an equivalent continuous-time ODE via matrix logarithm (Theorem 3) when the recurrence matrix is invertible with no eigenvalue equal to one | PLRNN emulating van-der-Pol oscillator · van-der-Pol example (Example 1) | agreement between discrete and continuous trajectories | No clear effect |
| Transform discrete-time PLRNN with eigenvalue equal to one into continuous time (Theorem 4) for long-term memory | 2-unit PLRNN solving the addition problem · addition problem (Example 2) | qualitative agreement of continuous and discrete solutions | No clear effect |
Closest papers by meaning
- Framing RNN as a kernel method: A neural ODE approach (NeurIPS 2021 · similarity 0.89)
- Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies (ICLR 2021 · similarity 0.89)
- Continuous-Time Piecewise-Linear Recurrent Neural Networks (ICML 2026 · similarity 0.89)
- Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction (NeurIPS 2024 · similarity 0.87)
- Inference of Neural Dynamics Using Switching Recurrent Neural Networks (NeurIPS 2024 · similarity 0.87)
- Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction (NeurIPS 2026 · 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.