Research map / Time series / Causal and generative time series
Unfolding recurrence by Green’s functions for optimized reservoir computing
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 |
|---|---|---|---|
| Optimize the input projection instead of using a random projection | Linear reservoir with optimized readout · ECG5000 | soft margin κη: 0.182±0.015 -> 0.383±0.026 | Helped |
| Optimize the input projection instead of using a random projection | Non-linear reservoir with optimized readout · ECG5000 | soft margin κη: 0.183±0.015 -> 0.384±0.026 | Helped |
| Optimize the input projection instead of using a random projection | Linear reservoir with optimized readout · ECG5000 | accuracy: (91.7±0.6)\,\% -> (97.3\pm0.4)\,\% | Helped |
| Optimize the input projection instead of using a random projection | Non-linear reservoir with optimized readout · ECG5000 | accuracy: (91.7±0.7)\,\% -> (97,3\pm0.4)\,\% | Helped |
| Add weak neuronal non-linearity | Reservoir with optimized input projection · ECG5000 | accuracy: (97.3\pm0.4)\,\% vs (97,3\pm0.4)\,\% | No clear effect |
| Add weak neuronal non-linearity | Reservoir with optimized input projection · Low-linear-separability stimuli | soft margin κη | Helped |
| Use random rather than optimized input projections | Non-linear reservoir · Stimulus separability varied | soft margin κη | Mixed |
Closest papers by meaning
- Learning dynamics in linear recurrent neural networks (ICML 2025 · similarity 0.88)
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · similarity 0.88)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.88)
- Inference of Neural Dynamics Using Switching Recurrent Neural Networks (NeurIPS 2024 · similarity 0.88)
- Unconditional stability of a recurrent neural circuit implementing divisive normalization (NeurIPS 2024 · similarity 0.88)
- Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks (ICLR 2024 · 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.