LFADS - Latent Factor Analysis via Dynamical Systems
arXiv:1608.06315
Abstract
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.
16 pages, 11 figures
References in corpus (9)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Improving neural networks by preventing co-adaptation of feature detectors
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Recurrent Neural Network Regularization
- DRAW: A Recurrent Neural Network For Image Generation
- Demixed principal component analysis of population activity in higher cortical areas reveals independent representation of task parameters
- Recurrent Network Models Of Sequence Generation And Memory
- Deep Kalman Filters
- Linear dynamical neural population models through nonlinear embeddings
Cited by in corpus (10)
- Recurrent switching linear dynamical systems
- Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
- Representation learning for neural population activity with Neural Data Transformers
- Targeted Neural Dynamical Modeling
- Nonlinear Evolution via Spatially-Dependent Linear Dynamics for Electrophysiology and Calcium Data
- Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time
- Variational online learning of neural dynamics
- Modeling neural dynamics during speech production using a state space variational autoencoder
- Ensemble Kalman Variational Objectives: Nonlinear Latent Trajectory Inference with A Hybrid of Variational Inference and Ensemble Kalman Filter
- Fitting summary statistics of neural data with a differentiable spiking network simulator