Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Estimating Nonlinear Neural Response Functions using GP Priors and Kronecker Methods
Cristina Savin, Gasper Tkacik
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 |
|---|---|---|---|
| Use spectral mixture kernel (5 components) instead of SE kernel for structured tuning | GP estimator on hexagonal grid artificial data · Extrapolation and stereotyped behaviour simulations | recovery of hexagonal lattice beyond observed region | Improved |
| Use GP with SE kernel or traditional methods instead of spectral mixture kernel for extrapolation | Traditional methods incl. GP-based inference with SE kernel · Extrapolation on hexagonal grid artificial data | extrapolation of spatial tuning | Hurt |
| Replace histogram estimate with GP posterior (SE kernel) for place field estimation | Artificial 2D random walk place fields · Artificial data, 10min sessions | fidelity to ground truth place field | Improved |
| Joint 3D GP estimation vs. separate conditional fields; Kronecker GP scaling | Kronecker GP estimator · Computational cost comparison | computing cost scaling | Improved |
| Use lower-cost Kronecker GP instead of standard O(N^3) GP | GP inference for neural tuning · Data size handled | maximum data size | Improved |
| Add network state (population spike count) as third input dimension | CA1 place field GP estimates · CA1 open field recordings | spatial information modulation | No clear effect |
| Direction-of-motion conditioning on place fields | 2D CA1 place fields · CA1 open field, 10 cells | directional tuning invariance | No clear effect |
Closest papers by meaning
- Scalable inference of functional neural connectivity at submillisecond timescales (NeurIPS 2025 · similarity 0.88)
- Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems (NeurIPS 2024 · similarity 0.88)
- Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation (ICML 2024 · similarity 0.86)
- Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data (ICLR 2024 · similarity 0.86)
- Modeling Neural Activity with Conditionally Linear Dynamical Systems (NeurIPS 2025 · similarity 0.86)
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · 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.
