IP Library › Granted Patent US 12,724,485
Granted Patent B2
US 12,724,485 · App. 18/228,575 · Granted Sep 1, 2026

Systems, methods, and media for decoding observed spike counts for spiking cells

Inventors: Sean Perkins (New York, NY); Mark Churchland (New York, NY); Karen Schroeder (San Diego, CA)
Assignee: The Trustees of Columbia University in the City of New York
G06F3/015A61B5/372A61B5/397
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,724,485
App. No.
18/228,575
Granted
Sep 1, 2026
Kind
B2
Abstract

Mechanisms including: receiving a first set of observed spike counts (FSoOSCs) for the spiking cells; determining a set of probabilities (SoPs) by: retrieving the SoPs from stored information (SI); or calculating the SopS based on the SI, wherein the SI regards possible biological states (BSs) of a subject, wherein each of the possible BSs belongs to at least one of a plurality of time sequences (PoTSs) of BSs, wherein each of the PoTSs of BSs corresponds to a possible action of the subject, and wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells; identifying using a hardware processor a first identified BS of the subject from the possible BSs based on the FSoOSCs and the set of probabilities; and determining an action to be performed based on the first identified BS.

Claims (201)

1 . A method of decoding observed spike counts for spiking cells, comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying using a hardware processor a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

identifying a second identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determining a third identified biological state from at least the first identified biological state and the second identified biological state;

determining an action to be performed based on the third identified biological state; and

controlling a device based on the determined action to move relative to space around the subject.

2 . The method of claim 1 , wherein the identifying of the first identified biological state of the subject comprises identifying the first identified biological state based on the first set of observed spike counts, the set of probabilities, and a utility function.

3 . The method of claim 1 , wherein the spiking cells are muscle cells.

4 . The method of claim 1 , wherein the spiking cells are neurons.

5 . The method of claim 1 , wherein the probabilities are log-probabilities.

6 . The method of claim 1 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

7 . A method of decoding observed spike counts for spiking cells, comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying using a hardware processor a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determining an action to be performed based on the first identified biological state;

controlling a device based on the determined action to move relative to space around the subject;

receiving a subsequent set of observed spike counts for the spiking cells, wherein the subsequent set of observed spike counts are observed at a different time than the first set of observed spike counts are observed; and

identifying a subsequent identified biological state of the subject from the possible biological states based on the subsequent set of observed spike counts, the first set of observed spike counts, and the set of probabilities.

8 . The method of claim 7 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

9 . A method of decoding observed spike counts for spiking cells, comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying using a hardware processor a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities, wherein the identifying of the first identified biological state of the subject comprises:

for each of the possible biological states in each of the plurality of time sequences of biological states:

retrieving or calculating a spiking cell probability for each of the spiking cells by matching the first set of observed spike counts to corresponding stored information for the possible biological state; and

calculating a combined probability that the first set of spike counts corresponds to the possible biological state based on a combination of the spiking cell probabilities;

determining an action to be performed based on the first identified biological state; and

controlling a device based on the determined action to move relative to space around the subject.

10 . The method of claim 9 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

11 . A system for decoding observed spike counts for spiking cells, comprising:

a memory; and

a hardware processor coupled to the memory and configured to:

receive a first set of observed spike counts for the spiking cells;

determine a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identify a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

identify a second identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determine a third identified biological state from at least the first identified biological state and the second identified biological state;

determine an action to be performed based on the third identified biological state; and

control a device based on the determined action to move relative to space around the subject.

12 . The system of claim 11 , wherein the identifying of the of first identified biological state of the subject comprises identifying the first identified biological state based on the first set of observed spike counts, the set of probabilities, and a utility function.

13 . The system of claim 11 , wherein the spiking cells are muscle cells.

14 . The system of claim 11 , wherein the spiking cells are neurons.

15 . The system of claim 11 , wherein the probabilities are log-probabilities.

16 . The system of claim 11 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

17 . A system for decoding observed spike counts for spiking cells, comprising:

a memory; and

a hardware processor coupled to the memory and configured to:

receive a first set of observed spike counts for the spiking cells;

determine a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identify a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determine an action to be performed based on the first identified biological state;

control a device based on the determined action to move relative to space around the subject;

receive a subsequent set of observed spike counts for the spiking cells, wherein the subsequent set of observed spike counts are observed at a different time than the first set of observed spike counts are observed; and

identify a subsequent identified biological state of the subject from the possible biological states based on the subsequent set of observed spike counts, the first set of observed spike counts, and the set of probabilities.

18 . The system of claim 17 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

19 . A system for decoding observed spike counts for spiking cells, comprising:

a memory; and

a hardware processor coupled to the memory and configured to:

receive a first set of observed spike counts for the spiking cells;

determine a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identify a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities, wherein the identifying of the first identified biological state of the subject comprises:

for each of the possible biological states in each of the plurality of time sequences of biological states:

 retrieving or calculating a spiking cell probability for each of the spiking cells by matching the first set of observed spike counts to corresponding stored information for the possible biological state; and

 calculating a combined probability that the first set of spike counts corresponds to the possible biological state based on a combination of the spiking cell probabilities;

determine an action to be performed based on the first identified biological state; and

control a device based on the determined action to move relative to space around the subject.

20 . The system of claim 19 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

21 . A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method of decoding observed spike counts for spiking cells, the method comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

identifying a second identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determining a third identified biological state from at least the first identified biological state and the second identified biological state;

determining an action to be performed based on the third identified biological state; and

controlling a device based on the determined action to move relative to space around the subject.

22 . The non-transitory computer-readable medium of claim 21 , wherein the identifying of the first identified biological state of the subject comprises identifying the first identified biological state based on the first set of observed spike counts, the set of probabilities, and a utility function.

23 . The non-transitory computer-readable medium of claim 21 , wherein the spiking cells are muscle cells.

24 . The non-transitory computer-readable medium of claim 21 , wherein the spiking cells are neurons.

25 . The non-transitory computer-readable medium of claim 21 , wherein the probabilities are log-probabilities.

26 . The non-transitory computer-readable medium of claim 21 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

27 . A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method of decoding observed spike counts for spiking cells, the method comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities;

determining an action to be performed based on the first identified biological state;

controlling a device based on the determined action to move relative to space around the subject;

receiving a subsequent set of observed spike counts for the spiking cells, wherein the subsequent set of observed spike counts are observed at a different time than the first set of observed spike counts are observed; and

identifying a subsequent identified biological state of the subject from the possible biological states based on the subsequent set of observed spike counts, the first set of observed spike counts, and the set of probabilities.

28 . The non-transitory computer-readable medium of claim 27 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

29 . A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method of decoding observed spike counts for spiking cells, the method comprising:

receiving a first set of observed spike counts for the spiking cells;

determining a set of probabilities by:

retrieving the set of probabilities from stored information; or

calculating the set of probabilities based on the stored information,

wherein the stored information regards possible biological states of a subject,

wherein each of the possible biological states belongs to at least one of a plurality of time sequences of biological states,

wherein each of the plurality of time sequences of biological states corresponds to a different possible action of the subject, and

wherein each probability in the set of probabilities indicates a likelihood of observing a possible spike count for one of the plurality of spiking cells at one of the possible biological states of one of the plurality of time sequences of biological states;

identifying a first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities, wherein the identifying of the first identified biological state of the subject comprises:

for each of the possible biological states in each of the plurality of time sequences of biological states:

retrieving or calculating a spiking cell probability for each of the spiking cells by matching the first set of observed spike counts to corresponding stored information for the possible biological state; and

calculating a combined probability that the first set of spike counts corresponds to the possible biological state based on a combination of the spiking cell probabilities;

determining an action to be performed based on the first identified biological state; and

controlling a device based on the determined action to move relative to space around the subject.

30 . The non-transitory computer-readable medium of claim 29 , wherein the identifying the first identified biological state of the subject from the possible biological states based on the first set of observed spike counts and the set of probabilities is performed by:

determining a first probability of the first set of observed spike counts corresponding to a first of the possible biological states in a first of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the first of the possible biological states,

determining a second probability of the first set of observed spike counts corresponding to a second of the possible biological states in a second of the plurality of time sequences of biological states based on probabilities of each of the first set of observed spike counts being observed for the second of the possible biological states,

determining that the first probability is higher than the second probability, and

in response to determining that the first probability is higher than the second probability, identifying the first identified biological state as being the first of the possible biological states,

wherein the first of the plurality of time sequences of biological states corresponds to a different action than the second of the plurality of time sequences of biological states.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 5, 2024
From: PERKINS, SEAN; CHURCHLAND, MARK; SCHROEDER, KAREN
To: THE TRUSTEES OF COLUMBIA UNIVERSITY IN THE CITY OF NEW YORK
Reel/Frame 067024/0020 →
Continuity (5)
Continuation In Part PCTUS2022014608 · Jan 31, 2022
Provisional Application 63456216 · Mar 31, 2023
Provisional Application 63210441 · Jun 14, 2021
Provisional Application 63143568 · Jan 29, 2021
Related Publication 20230376115A1 · Nov 23, 2023
References Cited (142)
US 7058445B2 · Kemere et al. · 2006 [cited by applicant]
US 7392079B2 · Donoghue · 2008 [cited by examiner]
US 7442212B2 · Richmond et al. · 2008 [cited by applicant]
US 9095455B2 · Kao et al. · 2015 [cited by applicant]
US 9195934B1 · Hunt et al. · 2015 [cited by applicant]
US 9373088B2 · Nuyujukian et al. · 2016 [cited by applicant]
US 10448877B2 · Truccolo · 2019 [cited by examiner]
US 10653330B2 · Angle et al. · 2020 [cited by applicant]
US 20140032459A1 · Sinyavskiy · 2014 [cited by examiner]
US 20140081895A1 · Coenen · 2014 [cited by examiner]
US 20140108302A1 · Chang et al. · 2014 [cited by applicant]
US 20140257520A1 · Kao · 2014 [cited by examiner]
US 20140330404A1 · Abdelghani · 2014 [cited by examiner]
US 20200097081A1 · Stone et al. · 2020 [cited by applicant]
US 20200268296A1 · Alcaide et al. · 2020 [cited by applicant]
US 20210004085A1 · Ketz et al. · 2021 [cited by applicant]
US 20210076963A1 · Yang · 2021 [cited by examiner]
US 20210365114A1 · Hewage · 2021 [cited by examiner]
US 20240192776A1 · Griggs · 2024 [cited by examiner]
WO WO2003005934 · 2003 [cited by applicant]
WO WO2007120819A2 · 2007 [cited by examiner]
WO WO2008137346A2 · 2008 [cited by examiner]
WO WO2012141714A1 · 2012 [cited by examiner]
WO WO20200152359 · 2020 [cited by applicant]
Yu et al. “Neural Decoding for Motor and Communication”, 2010, Elsevier, p. 219-263. (Year: 2010). [cited by examiner]
Ahmadi, N., et al., “Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning”, in Journal of Neural Engineering, vol. 18, No. 2, Feb. 26, 2021, pp. 1-24. [cited by applicant]
Ajiboye, A. B., et al., “Restoration of reaching and grasping movements through brain-controlled muscle stimulation in a person with tetraplegia: a proof-of-concept demonstration”, in The Lancet, vol. 389, No. 10081, Ma… [cited by applicant]
Altan, E., et al., “Estimating the dimensionality of the manifold underlying multi-electrode neural recordings”, in PLoS Computational Biology, vol. 17. No. 11, Nov. 29, 2021, pp. 1-23. [cited by applicant]
Anumanchipalli, G. K., et al., “Speech synthesis from neural decoding of spoken sentences”, in Nature vol. 568, Apr. 24, 2019, pp. 493-498. [cited by applicant]
Athalye, V. R., et al., “The brain uses invariant dynamics to generalize outputs across movements”, Technical Report, bioRxiv, Cold Spring Harbor Laboratory, Aug. 28, 2021, pp. 1-75. [cited by applicant]
Bouton, C. E., et al., “Restoring cortical control of functional movement in a human with quadriplegia”, in Nature, vol. 533, Apr. 13, 2016, pp. 1-13. [cited by applicant]
Brennan, C., et al., “One dimensional approximations of neuronal dynamics reveal computational strategy”, in PLOS Computational Biology, vol. 19 No. 1, Jan. 6, 2023, pp. 1-27. [cited by applicant]
Brockwell, A. E., et al., “Recursive Bayesian Decoding of Motor Cortical Signals by Particle Filtering”, in Journal of Neurophysiology, vol. 91, No. 4, Apr. 1, 2004, pp. 1899-1907. [cited by applicant]
Carmena, J. M., et al., “Learning to Control a Brain-Machine Interface for Reaching and Grasping by Primates”, In PLoS Biology, vol. 1.2, Oct. 13, 2003, pp. 1-16. [cited by applicant]
Chari, A., et al., “Microelectrode recordings in human epilepsy: A case for clinical translation?”, in Brain Communications, vol. 2, No. 2, Jun. 13, 2020, pp. 1-14. [cited by applicant]
Chaudhuri, R., et al. “The intrinsic attractor manifold and population dynamics of a canonical cognitive circuit across waking and sleep”, in Nature Neuroscience, vol. 22, No. 9, Aug. 12, 2019, pp. 1512-1520. [cited by applicant]
Cho, K., et al., “Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation”, Technical Report, arXiv:1406.1078, Cornell University, Sep. 3, 2014, pp. 1-15. [cited by applicant]
Chowdhury, R. H., et al., “Area 2 of primary somatosensory cortex encodes kinematics of the whole arm”, in eLife, vol. 9, Jan. 23, 2020, pp. 1-31. [cited by applicant]
Christie, B. P., et al., “Comparison of spike sorting and thresholding of voltage waveforms for intracortical brain-machine interface performance”, in Journal of Neural Engineering, vol. 12, No. 1, Dec. 11, 2014, pp. 1-… [cited by applicant]
Churchland, M. M., “Extracting Computational Principles Governing the Relation between Brain Activity and Muscle Activity that are Conserved between Rodents and Primates”, NIH Grant 5U19NS104649-04, Sep. 25, 2017, Colum… [cited by applicant]
Churchland, M. M., and Shenoy, K. V., “Temporal Complexity and Heterogeneity of Single-Neuron Activity in Premotor and Motor Cortex”, in Journal of Neurophysiology, vol. 97, No. 6, Jun. 1, 2007, pp. 4235-4257. [cited by applicant]
Churchland, M. M., et al., “Cortical Preparatory Activity: Representation of Movement or First Cog in a Dynamical Machine?”, in Neuron, vol. 68, Nov. 4, 2010, pp. 387-400. [cited by applicant]
Churchland, M. M., et al., “Neural population dynamics during reaching”, in Nature, vol. 487, Jun. 3, 2012, pp. 1-23. [cited by applicant]
Collinger, J. L., et al., “High-performance neuroprosthetic control by an individual with tetraplegia”, in The Lancet, vol. 381, No. 9866, Dec. 17, 2012, pp. 557-564. [cited by applicant]
Cowley, B. R., et al., “DataHigh: graphical user interface for visualizing and interacting with high-dimensional neural activity”, in Journal of Neural Engineering, vol. 10, No. 6, Nov. 12, 2013, pp. 1-20. [cited by applicant]
Degenhart, A., et al., “Constraints on the time course of neural population activity”, in Cosyne 2020, Denver, CO, USA, Feb. 27-Mar. 1, 2020, pp. 1. [cited by applicant]
DePasquale, B., et al., “The centrality of population-level factors to network computation is demonstrated by a versatile approach for training spiking networks”, in Neuron, vol. 111, No. 5, Mar. 1, 2023, pp. 1-30. [cited by applicant]
Ethier, C., et al., “Restoration of grasp following paralysis through brain-controlled stimulation of muscles”, in Nature, vol. 485, Apr. 18, 2012, pp. 368-371. [cited by applicant]
Gallego, J. A., et al., “Neural Manifolds for the Control of Movement”, in Neuron, vol. 94, No. 5, Jun. 7, 2017, pp. 978-984. [cited by applicant]
Gao, P., et al., “A theory of multineuronal dimensionality, dynamics and measurement”, Technical Report, bioRxiv, Cold Spring Harbor Laboratory, Nov. 12, 2017, p. 1-50. [cited by applicant]
Gao, Y., et al., “High-dimensional neural spike train analysis with generalized count linear dynamical systems”, in Proceedings of Twenty-ninth Conference on Neural Information Processing Systems, Montreal, CA, Dec. 7-1… [cited by applicant]
Gilja, V., et al., “A high-performance neural prosthesis enabled by control algorithm design”, in Nature Neuroscience, vol. 15, No. 12, Nov. 18, 2012, pp. 1-7. [cited by applicant]
Glaser, J. I., et al., “Machine learning for neural decoding”, in eNeuro, vol. 7, No. 4, Jul. 31, 2020, pp. 1-16. [cited by applicant]
Golub, M. D., et al., “Learning by neural reassociation”, in Nature Neuroscience vol. 21, No. 4, Mar. 12, 2018, pp. 1-14. [cited by applicant]
Henderson, J. M., “Engaging New Cognitive and Motor Signals to Improve Communication Prostheses”, NIH Grant 2R01DC014034-06, Stanford University, Apr. 1, 2015, available at: https://reporter.nih.gov/project-details/9886… [cited by applicant]
Hochberg, L. R., et al., “Neuronal ensemble control of prosthetic devices by a human with tetraplegia”, in Nature, vol. 442, Jul. 13, 2006, pp. 164-171. [cited by applicant]
Hochberg, L. R., et al., “Reach and grasp by people with tetraplegia using a neurally controlled robotic arm”, in Nature, vol. 485, May 16, 2012, pp. 372-375. [cited by applicant]
International Preliminary Report on Patentability dated Jul. 31, 2023 in International Patent Application No. PCT/US2022/014608, pp. 1-6. [cited by applicant]
International Search Report and Written Opinion dated May 20, 2022 in International Patent Application No. PCT/US2022/014608, pp. 1-14. [cited by applicant]
Jarosiewicz, B., et al., “Virtual typing by people with tetraplegia using a self-calibrating intracortical brain-computer interface”, in Science Translational Medicine, vol. 7, No. 313, Nov. 11, 2015, pp. 1-11. [cited by applicant]
Kalman, R. E., “A New Approach to Linear Filtering and Prediction Problems”, in Journal of Basic Engineering, vol. 82, No. 1, Mar. 1, 1960, pp. 1-12. [cited by applicant]
Kao, J. C., et al., “A High-Performance Neural Prosthesis Incorporating Discrete State Selection With Hidden Markov Models”, in IEEE Transactions on Biomedical Engineering, vol. 64, No. 4, Jun. 21, 2016, pp. 935-945. [cited by applicant]
Kao, J. C., et al., “Single-trial dynamics of motor cortex and their applications to brain-machine interfaces”, in Nature Communications, vol. 6., No. 1, Jul. 29, 2015, pp. 1-12. [cited by applicant]
Kaufman, M. T., et al., “The Largest Response Component in the Motor Cortex Reflects Movement Timing but Not Movement Type”, in eNeuro, vol. 3, No. 4, Aug. 3, 2016, pp. 1-25. [cited by applicant]
Kemere C., et al., “Robust Neural Decoding of Reaching Movements for Prosthetic Systems”, in Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Sep. 17-21, 2… [cited by applicant]
Kemere, C. T., et al., “Decoding of plan and peri-movement neural signals in prosthetic systems”, in IEEE Workshop on Signal Processing Systems, San Diego, CA, USA, Oct. 16-18, 2002, pp. 276-283. [cited by applicant]
Kemere, C., et al., “Detecting Neural-State Transitions Using Hidden Markov Models for Motor Cortical Prostheses”, in Journal of Neurophysiology, vol. 100, No. 4, Oct. 1, 2008, pp. 2441-2452. [cited by applicant]
Kemere, C., et al., “Model-Based Decoding of Reaching Movements for Prosthetic Systems”, in The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Francisco, CA, USA, Sep. … [cited by applicant]
Kemere, C., et al., “Model-based neural decoding of reaching movements: a maximum likelihood approach”, in IEEE Transactions on Biomedical Engineering, vol. 51, No. 6, May 24, 2004, pp. 925-932. [cited by applicant]
Keshtkaran, M. R., et al., “A large-scale neural network training framework for generalized estimation of single-trial population dynamics”, in Nature Methods, vol. 19, Nov. 28, 2022, pp. 1-18. [cited by applicant]
Kingma, D. P., and Ba, J., “Adam: A Method for Stochastic Optimization”, Technical Report, arXiv:1412.6980v1, Cornell University, Dec. 22, 2014, pp. 1-9. [cited by applicant]
Le, T., and Shlizerman, E., “STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer”, Technical Report, arXiv.org, Cornell University, Jun. 9, 2022, pp. 1-12. [cited by applicant]
Li, Z., et al. “Unscented Kalman Filter for Brain-Machine Interfaces”, in PLoS ONE, vol. 4, No. 7, Jul. 15, 2009, pp. 1-18. [cited by applicant]
Libedinsky, C., et al., “Independent Mobility Achieved through a Wireless Brain-Machine Interface”, in PLOS ONE, Nov. 1, 2016, pp. 1-13. [cited by applicant]
Macke, J. H., et al., “Empirical models of spiking in neural populations”, in Proceedings of Twenty-fifth Conference on Neural Information Processing Systems, Grenada, ES, Dec. 12-17, 2011, pp. 1-9. [cited by applicant]
Makin, J. G., et al., “Superior arm-movement decoding from cortex with a new, unsupervised-learning algorithm”, in Journal of Neural Engineering, vol. 15, No. 2, Jan. 25, 2018, pp. 1-20. [cited by applicant]
Marshall, N. J., et al., “Flexible neural control of motor units”, in Nature Neuroscience, vol. 25, Oct. 10, 2022, pp. 1-13. [cited by applicant]
Miri, A., et al., “Behaviorally Selective Engagement of Short-Latency Effector Pathways by Motor Cortex”, in Neuron, vol. 95, No. 3, Jul. 20, 2017, pp. 1-26. [cited by applicant]
Mishne, G., et al., “Hierarchical Coupled-Geometry Analysis for Neuronal Structure and Activity Pattern Discovery”, in IEEE Journal of Selected Topics in Signal Processing, vol. 10, No. 7, Aug. 24, 2016, pp. 1238-1253. [cited by applicant]
Moore, T., “Large-Scale Recordings in Primate Prefrontal Cortex: Mechanisms of Value and Attention”, NIH Grant 1R01NS116623-01, Stanford University, Sep. 30, 2020, available at: https://reporter.nih.gov/project-details/… [cited by applicant]
Moritz, C. T., et al., “Direct control of paralysed muscles by cortical neurons”, in Nature vol. 456, Dec. 1, 2008, pp. 1-19. [cited by applicant]
Musallam, S., et al., “Cognitive Control Signals for Neural Prosthetics”, in Science, vol. 305, No. 5681, Jul. 9, 2004, pp. 258-262. [cited by applicant]
Musk, E., “An Integrated Brain-Machine Interface Platform with Thousands of Channels”, in the Journal of Medical Internet Resources, vol. 21, No. 10, Oct. 31, 2019, pp. 1-14. [cited by applicant]
Notice of Allowance dated Apr. 19, 2022 in U.S. Appl. No. 17/589,716, pp. 1-30. [cited by applicant]
Nuyujukian, P., et al., “A High-Performance Keyboard Neural Prosthesis Enabled by Task Optimization”, in IEEE Transactions on Biomedical Engineering, vol. 62, No. 1, Sep. 4, 2014, pp. 21-29. [cited by applicant]
Oby, E. R., et al., “New neural activity patterns emerge with long-term learning”, in Proceedings of the National Academy of Sciences, vol. 116, No. 30, Jun. 10, 2019, pp. 15210-15215. [cited by applicant]
Pandarinath, C., et al., “High performance communication by people with paralysis using an intracortical brain-computer interface”, in eLife, Feb. 21, 2017, pp. 1-27. [cited by applicant]
Pandarinath, C., et al., “Inferring single-trial neural population dynamics using sequential auto-encoders”, in Nature Methods, vol. 15, No. 10, Sep. 17, 2018, pp. 1-21. [cited by applicant]
Pei, F., et al., “Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity”, in Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems Track on Datasets … [cited by applicant]
Peixoto, D., et al., “Decoding and perturbing decision states in real time”, in Nature, vol. 591, Jan. 20, 2021, pp. 1-21. [cited by applicant]
Pohlmeyer, E. A., et al., “Prediction of upper limb muscle activity from motor cortical discharge during reaching”, in Journal of Neural Engineering, vol. 4, No. 4, Nov. 12, 2007, pp. 369-379. [cited by applicant]
Provenza, N. R., et al., “Decoding task engagement from distributed network electrophysiology in humans”, in Journal of Neural Engineering, vol. 16, No. 5, Aug. 16, 2019, pp. 1-17. [cited by applicant]
Rajangam, S., et al., “Wireless Cortical Brain-Machine Interface for Whole-Body Navigation in Primates”, in Scientific Reports, vol. 6, No. 1, Mar. 3, 2016, pp. 1-13. [cited by applicant]
Rao, R.P., “Towards Neural Co-Processors for the Brain: Combining Decoding and Encoding in Brain-Computer Interfaces”, in Current Opinion Neurobiology, vol. 55, Apr. 4, 2019, pp. 1-20. [cited by applicant]
Robertson, A., “I Tried the Wristband that lets you Control Computers with your Brain”, in The Verge, Jun. 6, 2018, pp. 1-14. [cited by applicant]
Russo, A. A., et al., “Motor Cortex Embeds Muscle-like Commands in an Untangled Population Response”, in Neuron, vol. 97, No. 4, Feb. 21, 2018, pp. 1-23. [cited by applicant]
Sadtler, P. T., et al., “Neural constraints on learning”, in Nature, vol. 512, Aug. 27, 2014, pp. 1-16. [cited by applicant]
Sani, O. G., et al., “Modeling behaviorally relevant neural dynamics enabled by preferential subspace identification”, in Nature Neuroscience, vol. 24, No. 1, Nov. 9, 2020, pp. 1-26. [cited by applicant]
Sani, O. G., et al., “Mood variations decoded from multi-site intracranial human brain activity”, in Nature Biotechnology, vol. 36, No. 10, Sep. 10, 2018, pp. 954-961. [cited by applicant]
Saxena, S., et al., “Motor cortex activity across movement speeds is predicted by network-level strategies for generating muscle activity”, Technical Report, bioRxiv, Cold Spring Harbor Laboratory, Feb. 2, 2021, pp. 1-4… [cited by applicant]
Schneider, S., et al., “Learnable latent embeddings for joint behavioral and neural analysis”, Technical Report, arXiv.org, Cornell University, Oct. 5, 2022, pp. 1-46. [cited by applicant]
Schroeder, K. E., et al., “Cortical Control of Virtual Self-Motion Using Task-Specific Subspaces”, in The Journal of Neuroscience, vol. 42, No. 2, Jan. 12, 2022, pp. 220-239. [cited by applicant]
Schwemmer, M. A., et al., “Meeting brain-computer interface user performance expectations using a deep neural network decoding framework”, in Nature Medicine, vol. 24, No. 11, Sep. 24, 2018, pp. 1-14. [cited by applicant]
Seely, J. S., et al., “Tensor Analysis Reveals Distinct Population Structure that Parallels the Different Computational Roles of Areas M1 and V1”, in PLoS Computational Biology, vol. 12, No. 11, Nov. 4, 2016, pp. 1-34. [cited by applicant]
Serruya, M. D., et al., “Instant neural control of a movement signal”, in Nature, vol. 416, Mar. 14, 2002, pp. 141-142. [cited by applicant]
Shanechi, M. M., et al., “Rapid control and feedback rates enhance neuroprosthetic control”, in Nature Communications, vol. 8, No. 1, Jan. 6, 2017, pp. 1-10. [cited by applicant]
Shanechi, M.M., “Brain-Machine Interfaces from Motor to Mood”, in Nature Neuroscience, vol. 22, No. 10, Oct. 2019, pp. 1554-1564. [cited by applicant]
Snoek, J., et al., “Practical Bayesian Optimization of Machine Learning Algorithms”, in Proceedings of the Twenty-sixth Conference on Neural Information Processing Systems, Lake Tahoe, NV, USA, Dec. 3-8, 2012, pp. 1-9. [cited by applicant]
Sohn, H., et al., “Bayesian Computation through Cortical Latent Dynamics”, in Neuron, vol. 103, No. 5, Jul. 15, 2019, pp. 1-20. [cited by applicant]
Stavisky, S.D., “Neural Ensemble Dynamics in Dorsal Motor Cortex during Speech in People with Paralysis”, in Elife, vol. 8, Dec. 10, 2019, pp. 1-31. [cited by applicant]
Sussillo, D., et al. “Making brain-machine interfaces robust to future neural variability”, in Nature Communications, vol. 7, No. 1, Dec. 13, 2016, pp. 1-13. [cited by applicant]
Sussillo, D., et al., “A recurrent neural network for closed-loop intracortical brain-machine interface decoders”, in Journal of Neural Engineering, vol. 9, No. 2, Mar. 19, 2012, pp. 1-10. [cited by applicant]
Taylor, D. M., et al., “Direct Cortical Control of 3D Neuroprosthetic Devices”, in Science, vol. 296, No. 5574, Jun. 7, 2002, pp. 1829-1832. [cited by applicant]
Trautmann, E., et al., “Motor Cortex Isolates Skill-Specific Dynamics in a Context Switching Task”, in Cosyne 2022, Lisbon, PT, Mar. 17-20, 2022, pp. 97. [cited by applicant]
Tseng, P., et al., “Decoding Movements from Cortical Ensemble Activity Using a Long Short-Term Memory Recurrent Network”, in Neural Computation, vol. 31, No. 6, Jun. 1, 2019, pp. 1085-1113. [cited by applicant]
VA Office of Research and Development, “Restoring High Dimensional Hand Function to Persons with Chronic High Tetraplegia”, Clinical Trial NCT03482310, Mar. 29, 2019, available at: https://clinicaltrials.gov/ct2/show/NC… [cited by applicant]
Velliste, M., et al., “Cortical control of a prosthetic arm for self-feeding”, in Nature, vol. 453, May 28, 2008, pp. 1098-1101. [cited by applicant]
Visconti, P., et al., “Technical Features and Functionalities of Myo Armband: An Overview on Related Literature and Advanced Applications of Myoelectric Armbands Mainly Focused on Arm Prostheses”, in International Journ… [cited by applicant]
Vyas, S., et al., “Computation Through Neural Population Dynamics”, in Annual Review of Neuroscience, vol. 43, Jul. 2020, pp. 1-29. [cited by applicant]
Wadlinger, B., et al., “Ten-dimensional anthropomorphic arm control in a human brain-machine interface: difficulties, solutions, and limitations”, in Journal of Neural Engineering vol. 12, No. 1, Dec. 16, 2014, pp. 1-17. [cited by applicant]
Wallis, J. D., “Decoding Cognitive Processes from Neural Ensembles”, in Trends in Cognitive Sciences, vol. 22, No. 12, Dec. 2018, pp. 1091-1102. [cited by applicant]
Warriner, C. L., et al., “Motor cortical influence relies on task-specific activity covariation”, in Cell Reports, vol. 40, No. 13, Sep. 27, 2022, p. 1-26. [cited by applicant]
Watanabe, R.N., et al., “Fast Oscillatory Commands from the Motor Cortex can be Decoded by the Spinal Cord for Force Control”, in Journal of Neuroscience, vol. 35, No. 40, Oct. 7, 2015, pp. 13687-13697. [cited by applicant]
Wessberg, J., et al., “Real-time prediction of hand trajectory by ensembles of cortical neurons in primates”, in Nature, vol. 408, Nov. 16, 2000, pp. 361-365. [cited by applicant]
Willett, F., et al., “A high-performance speech neuroprosthesis”, Techical Report, bioRxiv, Cold Spring Harbor Laboratory, Jan. 21, 2023, pp. 1-38. [cited by applicant]
Willett, F., et al., “High-performance brain-to-text communication via handwriting”, in Nature, vol. 593, May 12, 2021, pp. 1-18. [cited by applicant]
Williams, A. H., et al., “Discovering Precise Temporal Patterns in Large-Scale Neural Recordings through Robust and Interpretable Time Warping”, in Neuron, vol. 105, No. 2, Jan. 22, 2020, pp. 1-23. [cited by applicant]
Wilson, G. H., et al., “Decoding spoken English from intracortical electrode arrays in dorsal precentral gyrus”, in Journal of Neural Engineering, vol. 17, No. 6, Nov. 11, 2020, pp. 1-22. [cited by applicant]
Wu, W., et al., “Neural Decoding of Cursor Motion Using a Kalman Filter”, in Proceedings of Neural Information Processing Systems, Vancouver, CA, Dec. 9-12, 2002, pp. 1-8. [cited by applicant]
Ye, J., and Pandarinath, C., “Representation learning for neural population activity with Neural Data Transformers”, in Neurons, Behavior, Data Analysis, and Theory, vol. 5, No. 3, Aug. 11, 2021, pp. 1-18. [cited by applicant]
Yousefi, A., et al., “Decoding Hidden Cognitive States From Behavior and Physiology Using a Bayesian Approach”, in Neural Computation, vol. 31, No. 9, Sep. 1, 2019, pp. 1751-1788. [cited by applicant]
Yu, B. M., et al., “Gaussian-process factor analysis for low-dimensional single-trial analysis of neural population activity”, in Journal of Neurophysiology, vol. 102, Apr. 8, 2009, pp. 614-635. [cited by applicant]
Yu, B. M., et al., “Mixture of Trajectory Models for Neural Decoding of Goal-Directed Movements”, in Journal of Neurophysiology, vol. 97, No. 5, May 1, 2007, pp. 3763-3780. [cited by applicant]
Ames, K.C., and Churcland, M.M., “Motor Cortex Signals for each Arm are Mixed across Hemispheres and Neurons yet Partitioned within the Population Response”, In eLife, vol. 8, Oct. 2019, pp. 1-36. [cited by applicant]
Elsayed, G.F., et al., “Reorganization between Prepartory and Movement Population Repsonses in Motor Cortex”, In Nature Communications, vol. 7, Oct. 2016, pp. 1-15. [cited by applicant]
Extended European Search Report dated Feb. 3, 2025 in EP Patent Application No. 22746830.3, pp. 1-10. [cited by applicant]
Gao, P., and Ganguli, S., “On Simplicity and Complexity in the Brave New World of Large-Scale Neuroscience”, In Current Opinion in Neurobiology, vol. 32, Mar. 2015, pp. 148-155. [cited by applicant]
Hochreiter, S., and Schmidhuber, J., “Long Short-Term Memory”, In Neural Computation, vol. 9, No. 8, Nov. 1997, pp. 1735-1780. [cited by applicant]
Kaufman, M.T., et al., “Cortical Activity in the Null Space: permitting preparation without movement”, In Nature Neuroscience, vol. 17, No. 3, Mar. 2014, pp. 440-448. [cited by applicant]
Rosenblatt, F., “Principles of Neurodynamics: perceptrons and the theory of brain mechanisms”, Technical Report, Cornell Aeronautical Laboratory, Buffalo, NY, Mar. 1961, pp. 1-626. [cited by applicant]
Stringer, C., et al., “High-Dimensional Geometry of Population Responses in Visual Cortex”, In Nature, vol. 571, Jun. 2019, pp. 361-365. [cited by applicant]
Tieleman, T., and Hinton, G., “Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude”, In Coursera: Neural Networks for Machine Learning, 2012, last accessed Apr. 9, 2026, available at: h… [cited by applicant]