-
公开(公告)号：US11625611B2
公开(公告)日：2023-04-11
申请号：US16731331
申请日：2019-12-31
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Philip Edwin Watson
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student neural network. In one aspect, there is provided a method comprising: processing a training input using the student neural network to generate an output for the training input; processing the student neural network output using a discriminative neural network to generate a discriminative score for the student neural network output, wherein the discriminative score characterizes a prediction for whether the network input was generated using: (i) the student neural network, or (ii) a brain emulation neural network; and adjusting current values of the student neural network parameters using gradients of an objective function that depends on the discriminative score for the student neural network output.
-
公开(公告)号：US11620487B2
公开(公告)日：2023-04-04
申请号：US16776108
申请日：2020-01-29
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Philip Edwin Watson , Georgios Evangelopoulos
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a neural network architecture for performing a machine learning task. In one aspect, a method comprises: obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in a brain of a biological organism; generating data defining a plurality of candidate graphs based on the synaptic connectivity graph; determining, for each candidate graph, a performance measure on a machine learning task of a neural network having a neural network architecture that is specified by the candidate graph; and selecting a final neural network architecture for performing the machine learning task based on the performance measures.
-
公开(公告)号：US20220358348A1
公开(公告)日：2022-11-10
申请号：US17307667
申请日：2021-05-04
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Jeffrey Bush , Doris Tang
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a representation of an image captured by an onboard camera of a drone and providing the representation of the image to a drone image processing neural network having a brain emulation sub-network with an architecture that is specified by synaptic connectivity between neurons in a brain of a biological organism, including instantiating a respective artificial neuron corresponding to each biological neuron of multiple biological neurons, and instantiating a respective connection between each pair of artificial neurons that correspond to a pair of biological neurons that are connected by a synaptic connection, and processing the representation of the image using the drone image processing neural network having the brain emulation sub-network to generate a network output that defines a prediction characterizing the image captured by the onboard camera of the drone.
-
公开(公告)号：US20220062580A1
公开(公告)日：2022-03-03
申请号：US17003620
申请日：2020-08-26
Applicant: X Development LLC
Inventor： Vladimir Miskovic , Matthew Dixon Eisaman , Sarah Ann Laszlo , Thomas Peter Hunt
Abstract: A method including identifying an activity pattern of a subject's brain, determining, based on the identified activity pattern of the subject's brain and a target parameter, a set of stimulation parameters, generating, by two or more emitters and based on the set of stimulation parameters, a composite stimulation pattern at a portion of the subject's brain, wherein each of the two or more emitters generates a stimulation pattern using a different modality, measuring, by one or more sensors, a response from the portion of the subject's brain in response to the composite stimulation pattern; and dynamically adjusting, for each emitter and based on the measured response from the portion of the subject's brain, a set of stimulation parameters.
-
公开(公告)号：US20210298624A1
公开(公告)日：2021-09-30
申请号：US16829179
申请日：2020-03-25
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Jeffrey Bush , Bin Ni , Matthew Sibigtroth
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neuroanatomical tract visualization using synaptic connectivity graphs. In one aspect, a method comprises: presenting, to a user and through a display, a representation of a synaptic connectivity graph representing synaptic connectivity between neurons in a brain of a biological organism; receiving, from the user, data specifying a seed neuron in the brain; identifying a neuroanatomical tract corresponding to the seed neuron in the brain; and presenting, to the user and through the display, a geometric representation of at least a portion of the brain of the biological organism that visually distinguishes the neuroanatomical tract corresponding to the seed neuron at neuronal resolution.
-
Patent Agency Ranking
公开(公告)号：US20210201158A1
公开(公告)日：2021-07-01
申请号：US16731331
申请日：2019-12-31
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Philip Edwin Watson
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a student neural network. In one aspect, there is provided a method comprising: processing a training input using the student neural network to generate an output for the training input; processing the student neural network output using a discriminative neural network to generate a discriminative score for the student neural network output, wherein the discriminative score characterizes a prediction for whether the network input was generated using: (i) the student neural network, or (ii) a brain emulation neural network; and adjusting current values of the student neural network parameters using gradients of an objective function that depends on the discriminative score for the student neural network output.
-
公开(公告)号：US20200205740A1
公开(公告)日：2020-07-02
申请号：US16284561
申请日：2019-02-25
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Aysja Johnson , Georgios Evangelopoulos , Nina Thigpen , Yvonne Yip
IPC: A61B5/00 , G06N3/08 , A61B5/04 , A61B5/0478
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining feature sets for a first number of diagnostic trials performed with a patient for diagnostic testing, wherein each feature set includes one or more features of electroencephalogram (EEG) signals measured from the patient while the patient is presented with trial content known to stimulate one or more desired human brain systems. Iteratively providing different combinations of the feature sets as input data to a diagnostic machine learning model to obtain model outputs, each model output corresponding to a particular one of the combinations. Determining, based on the model outputs, a consistency metric, the consistency metric indicating whether a quantity of feature sets in the combinations is sufficient to produce accurate output from the diagnostic machine learning model. Selectively ending the diagnostic testing with the patient based on a value of the consistency metric.
-
公开(公告)号：US10671164B2
公开(公告)日：2020-06-02
申请号：US15855845
申请日：2017-12-27
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Gabriella Levine , Joseph Hollis Sargent , Phillip Yee
IPC: G06F3/01 , A61B5/04 , A61B5/0482 , A61B5/0484 , A61B5/00 , A61B5/0478 , G06F3/0482
Abstract: A method for analyzing electroencephalogram (EEG) signals is disclosed. Information associated with two or more options is presented to a user. EEG signals from a sensor coupled to the user are received contemporaneously to the user receiving information associated with the two or more options. The EEG signals are processed in real time to determine which one of the options was selected by the user. In response to determining which one of the options was selected by the user, an action from one or more possible actions associated with the information presented to the user is selected. An output associated with the selected action is then generated.
-
公开(公告)号：US20190196586A1
公开(公告)日：2019-06-27
申请号：US16126945
申请日：2018-09-10
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Cyrus Behroozi , Gabriella Levine , Brian John Adolf , Joseph Hollis Sargent , Phillip Yee , Philip Edwin Watson
IPC: G06F3/01 , G01N33/483 , G01N27/02 , G06F15/18
CPC classification number: G06F3/015 , A61B5/0006 , A61B5/04004 , A61B5/04012 , A61B5/0478 , A61B5/6814 , A61B5/7203 , A61B5/7225 , A61B5/7264 , G01N27/02 , G01N33/4836 , G06N20/00
Abstract: A method for generating an EEG signal is disclosed. Multiple signals from multiple electrodes applied to a user's scalp are measured. The signals correspond to electrical activity generated by the user's brain. Each of the signals is evaluated using a machine learning algorithm in real-time to determine a quality of each of the signals. One or more of the signals is selected based on quality in real-time to provide one or more selected signals. An EEG signal is outputted corresponding to the electrical activity based on the selected signals.
-
公开(公告)号：US20190192031A1
公开(公告)日：2019-06-27
申请号：US15856043
申请日：2017-12-27
Applicant: X Development LLC
Inventor： Sarah Ann Laszlo , Philip Edwin Watson , Gabriella Levine
IPC: A61B5/0478 , A61B5/04 , A61B5/00
Abstract: A method for obtaining an electroencephalogram (EEG) of a user is disclosed. A reference sensor is attached to the user by connecting a first component of the reference sensor to a second component of the reference sensor, at least a portion of the first component being sub-dermally implanted on or adjacent to a mastoid process of the user. At least one active sensor is attached to the user. A first signal is detected from the reference sensor simultaneously as a second signal is detected from the at least one active sensor. The EEG is obtained based on the first signal and the second signal.
-
-
-
-
-
-
-
-
-
Search Results
66
records
(took 0.037 seconds)
