Research map / Probabilistic and scientific modeling / Dynamical systems
Cross-Spectral Factor Analysis
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 |
|---|---|---|---|
| model time-varying covariance with CSFA instead of constant covariance | CSFA · Synthetic data | KL-divergence (lower better): 7560.2 -> 5466.8 | Helped |
| add supervised dCSFA discriminative factors vs unsupervised CSFA | dCSFA · Mouse genotype | AUROC: 0.685 -> 0.731 | Helped |
| add supervised dCSFA vs CSFA | dCSFA · Mouse behavioral context | accuracy (%): 82.8 -> 83.1 | No clear effect |
| restrict classifier to 3 discriminative dCSFA factors vs all dCSFA factors | dCSFA · Mouse genotype | AUROC: 0.731 -> 0.741 | Helped |
| restrict classifier to 3 dCSFA factors vs all | dCSFA · Mouse behavioral context | accuracy (%): 83.1 -> 70.7 | Hurt |
| dCSFA-3 vs Welch+PCA-3 with 3 features | dCSFA-3 · Mouse genotype | AUROC: 0.528 -> 0.741 | Helped |
| dCSFA-3 vs Welch+PCA-3 with 3 features | dCSFA-3 · Mouse behavioral context | accuracy (%): 54.7 -> 70.7 | Helped |
| use Welch+PCA instead of CSFA features | Welch + PCA · Mouse genotype | AUROC: 0.685 -> 0.922 | Helped |
| use FFT+PCA instead of CSFA features | FFT + PCA · Mouse behavioral context | accuracy (%): 82.8 -> 85.5 | Helped |
| use CSFA instead of FFT+PCA features | CSFA · Mouse genotype | AUROC: 0.632 -> 0.685 | Helped |
Closest papers by meaning
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.86)
- Accurate Identification of Communication Between Multiple Interacting Neural Populations (ICML 2025 · similarity 0.85)
- CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations (ICLR 2025 · similarity 0.85)
- Multi-Modal Latent Variables for Cross-Individual Primary Visual Cortex Modeling and Analysis (AAAI 2025 · similarity 0.84)
- Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data (ICLR 2024 · similarity 0.84)
- Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions (ICML 2024 · 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.