Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Tracking Functional Changes in Nonstationary Signals with Evolutionary Ensemble Bayesian Model for Robust Neural Decoding
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 |
|---|---|---|---|
| add DE-based model evolution (ablation) | EvoEnsemble · simulation conditions 1-5 | R2: 0.552, 0, 0.187, 0, 0.896 -> 0.975, 0.759, 0.970, 0.764, 0.986 | Helped |
| use EvoEnsemble instead of Kalman filter | state decoder · simulation conditions 1-5 | CC: 12.6%, 105.2%, 1.7%, 155.0%, and 4.7% higher | Helped |
| evolve-at-changes update instead of regular-interval update (ablation) | EvoEnsemble · simulation 4 | R2 and update cost: 0.741 comparable to 0.764; 72.2% fewer updates | No clear effect |
| vary update ratio rup from 0.4 to 0.9 (ablation) | EvoEnsemble · simulation 4 | R2 | No clear effect |
| add history-model-archive strategy (ablation) | EvoEnsemble · simulation conditions 1-5 | R2 | Helped |
| vary history preserve ratio rpre (ablation) | EvoEnsemble · simulation conditions 1-5 | R2 | Mixed |
| use EvoEnsemble instead of Kalman filter | state decoder · Data-M, Data-P1/2/3 | CC: 7.2%, 39.2%, 26.1% and 43.2% higher | Helped |
| use EvoEnsemble instead of Kalman filter (recalib) | state decoder · Data-M, Data-P1/2/3 | CC: 8.4%, 14.7%, 2.4% and 10.9% | Helped |
| use EvoEnsemble instead of DyEnsemble | state decoder · Data-M, Data-P1/2/3 | CC: 4.5%, 6.6%, 15.7% and 3.2% | Helped |
| add model evolution to ensemble without evolution (ablation) | EvoEnsemble · Data-P1/2 | CC: 6.6% and 15.7% | Helped |
| use dynamic ensemble (DyEnsemble) instead of static Kalman filter | decoder · Data-P1/2/3 | CC: 0.393, 0.445, 0.340 -> 0.513, 0.485, 0.472 | Helped |
| use periodic recalibration of Kalman filter | Kalman filter · Data-M, Data-P1/2/3 | CC: 0.713 -> 0.705 | Mixed |
Closest papers by meaning
- Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes (ICML 2025 · similarity 0.84)
- A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks (NeurIPS 2025 · similarity 0.84)
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.83)
- SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding (NeurIPS 2025 · similarity 0.83)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.82)
- EVOS: Efficient Implicit Neural Training via EVOlutionary Selector (CVPR 2025 · similarity 0.82)
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.