Research map / Probabilistic and scientific modeling / Dynamical systems
Linear dynamical neural population models through nonlinear embeddings
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 |
|---|---|---|---|
| Use a nonlinear observation function instead of a linear rate function | PfLDS versus PLDS · Grid-cell simulation | PLL: -0.622 -> -0.581 | Helped |
| Use a nonlinear observation function rather than a linear rate function | fLDS versus PLDS · Macaque V1, single orientation | predictive performance at a compact latent dimension | Helped |
| Use a nonlinear observation function rather than a linear rate function | fLDS versus PLDS · Macaque V1, full dataset | predictive performance | Helped |
| Use a nonlinear observation function rather than a linear rate function | PfLDS and GCfLDS versus their linear counterparts · Macaque center-out reaching | predictive NLL | Helped |
| Use a generalized-count observation model instead of a Poisson observation model | GCLDS and GCfLDS · Macaque center-out reaching | predictive likelihood | Helped |
| Use AEVB instead of LapEM or VBDual for inference | PLDS and GCLDS · Linear-observation simulations | PLL | No clear effect |
| Fit a flexible nonlinear model to data generated with a linear observation function | PfLDS and GCfLDS · Linear-observation simulations | PLL | No clear effect |
Closest papers by meaning
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.89)
- Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics (NeurIPS 2024 · similarity 0.89)
- Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems (NeurIPS 2024 · similarity 0.88)
- Inferring stochastic low-rank recurrent neural networks from neural data (NeurIPS 2024 · similarity 0.88)
- Modeling Neural Activity with Conditionally Linear Dynamical Systems (NeurIPS 2025 · similarity 0.88)
- Meta-Dynamical State Space Models for Integrative Neural Data Analysis (ICLR 2025 · similarity 0.87)
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.