Stabilizing brain-computer interfaces through alignment of latent dynamics
Open accessPreprint — published as 10.1038/s41467-025-59652-y
Abstract
Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices. In current iBCIs, instabilities at the neural interface result in a degradation of decoding performance, which necessitates frequent supervised recalibration using new labeled data. One potential solution is to use the latent manifold structure that underlies neural population activity to facilitate a stable mapping between brain activity and behavior. Recent efforts using unsupervised approaches have improved iBCI stability using this principle; however, existing methods treat each time step as an independent sample and do not account for latent dynamics. Dynamics have been used to enable high performance prediction of movement intention, and may also help improve stabilization. Here, we present a platform for Nonlinear Manifold Alignment with Dynamics (NoMAD), which stabilizes iBCI decoding using recurrent neural network models of dynamics. NoMAD uses unsupervised distribution alignment to update the mapping of nonstationary neural data to a consistent set of neural dynamics, thereby providing stable input to the iBCI decoder. In applications to data from monkey motor cortex collected during motor tasks, NoMAD enables accurate behavioral decoding with unparalleled stability over weeks-to months-long timescales without any supervised recalibration.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Models that learn an underlying manifold structure for a behaviour can be used to stabilize MEA activity over time.
“One line of work involves developing models that learn an underlying manifold (low-dimensional spaces that capture neural population dynamics) structure for a given behaviour103,104,121, which can then be used to stabilize MEA activity over time.”
From The speech neuroprosthesis (2024) · cites this paper as [104]
In “Leveraging manifolds and dynamics to stabilize iBCI decoding” (page unavailable), the paper describes learning a neural manifold and updating the mapping from recorded activity to that manifold across sessions. It supports stabilization of decoding despite changes in electrode recordings, but does not say the method stabilizes MEA activity itself. (LLM, conf=0.84)
Experimental — accuracy not yet measuredUnsupervised algorithms for updating decoders to neural changes should be feasible.
“Furthermore, we found that neural activity changed at a gradual rate over time, suggesting that unsupervised algorithms for updating decoders to neural changes should be feasible24–27 (Fig. 4d).”
From A high-performance speech neuroprosthesis (2023) · cites this paper as [27]
These results indicate that substantial gains in performance are probably still possible with further language model improvements and more robust decoding algorithms that generalize better to non-stationary data.
“These results indicate that substantial gains in performance are probably still possible with further language model improvements and more robust decoding algorithms that generalize better to non-stationary data (for example, unsupervised methods that track non-stationarities without the requirement for new training data24–27).”
From A high-performance speech neuroprosthesis (2023) · cites this paper as [27]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
References 64 · Cited by 71
Research works printed but not linked: 5
- Yu, B. M. et al. Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity. in Advances in Neural Information Processing Systems vol. 21 (Curran Associates, Inc., 2008).
- Dabagia, M., Kording, K. P. & Dyer, E. L. Comparing high-dimensional neural recordings by aligning their low-dimensional latent representations. Nat. Biomed. Eng. in press , 20.
- Lee, J., Dabagia, M., Dyer, E. L. & Rozell, C. J. Hierarchical Optimal Transport for Multimodal Distribution Alignment. Neural Inf. Process. Syst. NeurIPS (2019).
- Chung, J. et al. A Recurrent Latent Variable Model for Sequential Data. Adv. Neural Inf. Process. Syst. 28 , (2016).
- Keshtkaran, M. R. & Pandarinath, C. Enabling hyperparameter optimization in sequential autoencoders for spiking neural data. Adv. Neural Inf. Process. Syst. (2019).
- Authors
- Karpowicz, B. M., Ali, Y. H., Wimalasena, L. N., Sedler, A. R., Keshtkaran, M. R., Bodkin, K., Ma, X., Miller, L. E., & Pandarinath, C.
- Affiliations
- Georgia Institute of Technology (US)
- Northwestern University (US)
- Corresponding author
- Pandarinath, Chethan
- ORCID
- Venue
- Nature Communications
- Publisher
- openRxiv
- Published
- 2022-04-08
- Volume
- 16
- Issue
- 1
- Pages
- 4662-4662
- ISSN
- 2041-1723 (ISSN-L)
- OpenAlex
- W4410485388
- Cited by
- 71
- References
- 64
- Citations by year
- 2026: 27 · 2025: 25 · 2024: 11 · 2023: 6 · 2022: 2
- FWCI
- 29.45
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- Locations
- Nature Communications (publishedVersion, cc-by-nc-nd)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (DGE- 1,650,044, 1835364, 1650044)
- Burroughs Wellcome Fund
- Alfred P. Sloan Foundation
- Simons Foundation
- Emory University
- National Institutes of Health (DGE-1650044, 5u01dc017844-06)
- Defense Advanced Research Projects Agency (PA-18-02-04-INI-FP-021)
- National Institute on Drug Abuse (RF1DA055667)
- National Institute on Deafness and Other Communication Disorders (U01- DC017844)
- National Institute of Neurological Disorders and Stroke (R01NS074044, R01NS053603, DP2NS127291, #NS053603, NS-074044)
- National Institute of Biomedical Imaging and Bioengineering (T32EB025816)
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (K12HD073945)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Keywords
- intracortical brain-computer interfaces, latent dynamics, motor cortex, monkey motor cortex, paralysis
- MeSH terms
- Animals, Humans, Macaca mulatta, Male, Motor Cortex, Movement, Neural Networks, Computer, Brain-Computer Interfaces
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
