We show that nonlinear latent factors and structures in neural population activity can be modelled in a manner that allows for flexible dynamical inference, causally, non-causally and in the presence of missing neural observations. Further, the developed neural network model improves the prediction of neural activity, behaviour and latent neural structures.
This is a preview of subscription content, log in via an institution to check access.
References
Vyas, S., Golub, M. D., Sussillo, D. & Shenoy, K. V. Computation through neural population dynamics. Annu. Rev. Neurosci. 43, 249–275 (2020). This review article overviews the dynamical modelling of neural population activity.
Shanechi, M. M. Brain–machine interfaces from motor to mood. Nat. Neurosci. 22, 1554–1564 (2019). This perspective article presents the modelling directions and needs in neurotechnologies and brain–computer interfaces for neurological and neuropsychiatric disorders.
Pandarinath, C. et al. Inferring single-trial neural population dynamics using sequential auto-encoders. Nat. Methods 15, 805–815 (2018). This paper reports a competitive benchmark SAE for neural population activity termed LFADS, which performs non-causal, non-recursive inference.
Gao, Y., Archer, E. W., Paninski, L. & Cunningham, J. P. Linear dynamical neural population models through nonlinear embeddings. Adv. Neur. Info. Proces. Syst. 29, 163–171 (2016). This paper reports a competitive neural network with non-causal, non-recursive inference that consists of a linear dynamical model with a direct nonlinear observation.
Yang, Y. et al. Modelling and prediction of the dynamic responses of large-scale brain networks during direct electrical stimulation. Nat. Biomed. Eng. 5, 324–345 (2021). This paper reports a linear dynamical model of the effect of perturbation on neural dynamics.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This is a summary of: Abbaspourazad, H. et al. Dynamical flexible inference of nonlinear latent factors and structures in neural population activity. Nat. Biomed. Eng. https://doi.org/10.1038/s41551-023-01106-1 (2023).
Rights and permissions
About this article
Cite this article
A neural network that enables flexible nonlinear inference from neural population activity. Nat. Biomed. Eng 8, 9–10 (2024). https://doi.org/10.1038/s41551-023-01111-4
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41551-023-01111-4
- Springer Nature Limited