About this item:

420 Views | 332 Downloads

Author Notes:

Correspondence should be addressed to David Sussillo sussillo@google.com and Chethan Pandarinath chethan@gatech.edu.

C.P., D.J.O., and D.S. designed the study, performed analyses, and wrote the manuscript with input from all authors.

D.S. and L.F.A. developed the algorithmic approach.

C.P., J.C., and R.J. contributed to algorithmic development and analysis of synthetic data.

D.J.O., S.D.S., J.C.K., E.M.T., M.T.K., S.I.R., and K.V.S. performed research with monkeys.

C.P., L.R.H., K.V.S., and J.M.H. performed research with human research participants.

All authors contributed to revising the manuscript.

We would like to thank John P. Cunningham and Jascha Sohl-Dickstein for extensive conversation.

We thank Mark M. Churchland for contributions to data collection for monkey J, Christine Blabe and Paul Nuyujukian for assistance with research sessions with participant T5, Emad Eskandar for array implantation with participant T7, and Brittany Sorice and Anish Sarma for assistance with research sessions with participant T7.

R.J. participated in this work while at Google, Inc.

J.M.H is on the Medical Advisory Boards of Enspire DBS and Circuit Therapeutics, and the Surgical Advisory Board for Neuropace, Inc. K.V.S. is a consultant to Neuralink Corp. and on the Scientific Advisory Boards of CTRL-Labs, Inc. and Heal, Inc.; these entities did not support this work.

The authors declare no competing financial interests.


Research Funding:

L.F.A.’s research was supported by US National Institutes of Health grant MH093338, the Gatsby Charitable Foundation through the Gatsby Initiative in Brain Circuitry at Columbia University, the Simons Foundation, the Swartz Foundation, the Harold and Leila Y. Mathers Foundation, and the Kavli Institute for Brain Science at Columbia University.

C.P. was supported by a postdoctoral fellowship from the Craig H. Neilsen Foundation for spinal cord injury research and the Stanford Dean’s Fellowship.

S.D.S. was supported by the ALS Association’s Milton Safenowitz Postdoctoral Fellowship.

K.V.S.’s research was supported by the following awards: an NIH-NINDS award (T-R01NS076460), an NIH-NIMH award (T-R01MH09964703), an NIH Director’s Pioneer award (8DP1HD075623), a DARPA-DSO ‘REPAIR’ award (N66001–10-C-2010), a DARPA-BTO ‘NeuroFAST’ award (W911NF-14–2-0013), a Simons Foundation Collaboration on the Global Brain award (325380), and the Howard Hughes Medical Institute.

J.M.H.’s research was supported by NIH-NIDCD R01DC014034.

K.V.S. and J.M.H.’s research was supported by Stanford BioX-NeuroVentures, Stanford Institute for Neuro-Innovation and Translational Neuroscience, Garlick Foundation and Reeve Foundation.

L.R.H’s research was supported by NIH-NIDCD R01DC009899, Rehabilitation Research and Development Service, Department of Veterans Affairs (B6453R), MGH-Deane Institute for Integrated Research on Atrial Fibrillation and Stroke; Executive Committee on Research, Massachusetts General Hospital.


  • Science & Technology
  • Life Sciences & Biomedicine
  • Biochemical Research Methods
  • Biochemistry & Molecular Biology

Inferring single-trial neural population dynamics using sequential auto-encoders

Show all authors Show less authors

Journal Title:

Nature Methods


Volume 15, Number 10


, Pages 805-+

Type of Work:

Article | Post-print: After Peer Review


Neuroscience is experiencing a revolution in which simultaneous recording of thousands of neurons is revealing population dynamics that are not apparent from single-neuron responses. This structure is typically extracted from data averaged across many trials, but deeper understanding requires studying phenomena detected in single trials, which is challenging due to incomplete sampling of the neural population, trial-to-trial variability, and fluctuations in action potential timing. We introduce latent factor analysis via dynamical systems, a deep learning method to infer latent dynamics from single-trial neural spiking data. When applied to a variety of macaque and human motor cortical datasets, latent factor analysis via dynamical systems accurately predicts observed behavioral variables, extracts precise firing rate estimates of neural dynamics on single trials, infers perturbations to those dynamics that correlate with behavioral choices, and combines data from non-overlapping recording sessions spanning months to improve inference of underlying dynamics.

Copyright information:

© 2018, The Author(s), under exclusive licence to Springer Nature America, Inc.

Export to EndNote