Skip to main content

Bubblewrap: Online tiling and real-time flow prediction on neural manifolds.

Publication ,  Conference
Draelos, A; Gupta, P; Jun, NY; Sriworarat, C; Pearson, J
Published in: Adv Neural Inf Process Syst
December 2021

While most classic studies of function in experimental neuroscience have focused on the coding properties of individual neurons, recent developments in recording technologies have resulted in an increasing emphasis on the dynamics of neural populations. This has given rise to a wide variety of models for analyzing population activity in relation to experimental variables, but direct testing of many neural population hypotheses requires intervening in the system based on current neural state, necessitating models capable of inferring neural state online. Existing approaches, primarily based on dynamical systems, require strong parametric assumptions that are easily violated in the noise-dominated regime and do not scale well to the thousands of data channels in modern experiments. To address this problem, we propose a method that combines fast, stable dimensionality reduction with a soft tiling of the resulting neural manifold, allowing dynamics to be approximated as a probability flow between tiles. This method can be fit efficiently using online expectation maximization, scales to tens of thousands of tiles, and outperforms existing methods when dynamics are noise-dominated or feature multi-modal transition probabilities. The resulting model can be trained at kiloHertz data rates, produces accurate approximations of neural dynamics within minutes, and generates predictions on submillisecond time scales. It retains predictive performance throughout many time steps into the future and is fast enough to serve as a component of closed-loop causal experiments.

Duke Scholars

Published In

Adv Neural Inf Process Syst

ISSN

1049-5258

Publication Date

December 2021

Volume

34

Start / End Page

6062 / 6074

Location

United States

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Draelos, A., Gupta, P., Jun, N. Y., Sriworarat, C., & Pearson, J. (2021). Bubblewrap: Online tiling and real-time flow prediction on neural manifolds. In Adv Neural Inf Process Syst (Vol. 34, pp. 6062–6074). United States.
Draelos, Anne, Pranjal Gupta, Na Young Jun, Chaichontat Sriworarat, and John Pearson. “Bubblewrap: Online tiling and real-time flow prediction on neural manifolds.” In Adv Neural Inf Process Syst, 34:6062–74, 2021.
Draelos A, Gupta P, Jun NY, Sriworarat C, Pearson J. Bubblewrap: Online tiling and real-time flow prediction on neural manifolds. In: Adv Neural Inf Process Syst. 2021. p. 6062–74.
Draelos, Anne, et al. “Bubblewrap: Online tiling and real-time flow prediction on neural manifolds.Adv Neural Inf Process Syst, vol. 34, 2021, pp. 6062–74.
Draelos A, Gupta P, Jun NY, Sriworarat C, Pearson J. Bubblewrap: Online tiling and real-time flow prediction on neural manifolds. Adv Neural Inf Process Syst. 2021. p. 6062–6074.

Published In

Adv Neural Inf Process Syst

ISSN

1049-5258

Publication Date

December 2021

Volume

34

Start / End Page

6062 / 6074

Location

United States

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology