LFADS - Latent Factor Analysis via Dynamical Systems
This addresses the challenge of analyzing large-scale neural recordings for neuroscience, though it appears incremental as it builds on existing sequential and variational auto-encoder models.
The authors tackled the problem of analyzing high-dimensional neural spiking data by introducing LFADS, a method that infers latent dynamics, and showed it significantly outperforms existing methods in inferring neural firing rates and latent dynamics on synthetic data.
Neuroscience is experiencing a data revolution in which many hundreds or thousands of neurons are recorded simultaneously. Currently, there is little consensus on how such data should be analyzed. Here we introduce LFADS (Latent Factor Analysis via Dynamical Systems), a method to infer latent dynamics from simultaneously recorded, single-trial, high-dimensional neural spiking data. LFADS is a sequential model based on a variational auto-encoder. By making a dynamical systems hypothesis regarding the generation of the observed data, LFADS reduces observed spiking to a set of low-dimensional temporal factors, per-trial initial conditions, and inferred inputs. We compare LFADS to existing methods on synthetic data and show that it significantly out-performs them in inferring neural firing rates and latent dynamics.