Model Documentation

These pages are generated from registered model config classes, model class docstrings, and config field defaults.

After editing a model docstring or config, regenerate these files with:

python scripts/generate_model_docs.py

Model	Registry Name	Summary
BGPFA	bgpfa	Variational Bayesian GPFA with ARD and differentiable ELBO training.
CASSM	cassm	Thin wrapper around the bundled CASSM sparse filter/smoother.
GPFA	gpfa	Gaussian Process Factor Analysis with diagonal observation noise.
ILQRVAE	ilqr_vae	Optimization-based iLQR-VAE with posterior-control inference and ELBO training.
Kalman	kalman	Dense Kalman filter baseline adapted from the CASSM source.
LangevinFlow	langevin_flow	LangevinFlow sequential VAE for binned neural spike counts.
LFADS	lfads	Latent Factor Analysis via Dynamical Systems for binned spike counts.
MINT	mint	Mesh of Idealized Neural Trajectories adapted to the LaDyS API.
NDT	ndt	Transformer encoder trained with a masked Poisson spike objective.
PSTH	psth	Peri-stimulus time histogram baseline.
Smoothing	smoothing	Gaussian-smoothed spike-count baseline.
STNDT	stndt	Spatiotemporal Neural Data Transformer for binned spike counts.