Neural Dynamics Discovery via Gaussian Process Recurrent Neural Networks

Abstract

Latent dynamics discovery is challenging in extracting complex dynamics from high-dimensional noisy neural data. Many dimensionality reduction methods have been widely adopted to extract low-dimensional, smooth and time-evolving latent trajectories. However, simple state transition structures, linear embedding assumptions, or inflexible inference networks impede the accurate recovery of dynamic portraits. In this paper, we propose a novel latent dynamic model that is capable of capturing nonlinear, non-Markovian, long short-term time-dependent dynamics via recurrent neural networks and tackling complex nonlinear embedding via non-parametric Gaussian process. Due to the complexity and intractability of the model and its inference, we also provide a powerful inference network with bi-directional long short-term memory networks that encode both past and future information into posterior distributions. In the experiment, we show that our model outperforms other state-of-the-art methods in reconstructing insightful latent dynamics from both simulated and experimental neural datasets with either Gaussian or Poisson observations, especially in the low-sample scenario. Our codes and additional materials are available at https://github.com/sheqi/GP-RNN_UAI2019.

11 pages, 3 figures, 7 Tables, accepted to The Conference on Uncertainty in Artificial Intelligence (UAI), 2019

References in corpus (4)

• DRAW: A Recurrent Neural Network For Image Generation
• A Recurrent Latent Variable Model for Sequential Data
• Black box variational inference for state space models
• Recurrent Gaussian Processes

Cited by in corpus (6)

• Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity
• Building population models for large-scale neural recordings: opportunities and pitfalls
• Representation learning for neural population activity with Neural Data Transformers
• OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning
• An Efficient and Flexible Spike Train Model via Empirical Bayes
• Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems