Research map / Probabilistic and scientific modeling / Dynamical systems
LERD: Latent Event-Relational Dynamics for Neurodegenerative Classification
Yicheng Feng, Hairong Chen, Ziyu Jia, Samir Bhatt, Hengguan Huang
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 |
|---|---|---|---|
| add dLIF prior (ablation) | LERD · AD cohort A | accuracy (%): 70.52 -> 73.92 | Improved |
| add ERG prior (ablation) | LERD · AD cohort A | accuracy (%): 70.52 -> 72.75 | Improved |
| combine dLIF and ERG priors (ablation) | LERD · AD cohort A | accuracy (%): 70.52 -> 75.03 | Improved |
| add dLIF prior (ablation) | LERD · AD cohort B | accuracy (%): 83.22 -> 87.98 | Improved |
| add ERG prior (ablation) | LERD · AD cohort B | F1 (%): 60.72 -> 65.63 | Improved |
| combine dLIF and ERG priors (ablation) | LERD · AD cohort B | accuracy (%): 83.22 -> 89.82 | Improved |
| combine both priors vs ERG prior only (ablation) | LERD · AD cohort B | F1 (%): 65.63 -> 64.87 | No clear effect |
| use LERD over best baseline | LERD · AD cohort A | accuracy (%): 72.68 -> 75.03 | Improved |
| use LERD over best baseline | LERD · AD cohort B | accuracy (%): 82.38 -> 89.82 | Improved |
| use LERD latent events instead of NODE/ODE-RNN/STRODE | LERD · Toy dataset [5, 10] Hz | boundary IoU: 0.000 -> 0.473 | Improved |
| use LERD instead of EEGNet in cosine similarity | LERD · Toy dataset | cosine similarity: 0.967 -> 0.983 | No clear effect |
Closest papers by meaning
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.85)
- THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations (NeurIPS 2025 · similarity 0.85)
- CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations (ICLR 2025 · similarity 0.85)
- BrainLM: A foundation model for brain activity recordings (ICLR 2024 · similarity 0.84)
- Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series (ICML 2025 · similarity 0.84)
- Accurate Identification of Communication Between Multiple Interacting Neural Populations (ICML 2025 · similarity 0.84)
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.
