中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

2328 records (took 0.034 seconds)

    TRAINING BRAIN EMULATION NEURAL NETWORKS USING BIOLOGICALLY-PLAUSIBLE ALGORITHMS
    72.
    发明公开
    TRAINING BRAIN EMULATION NEURAL NETWORKS USING BIOLOGICALLY-PLAUSIBLE ALGORITHMS 审中-公开

    公开(公告)号：US20230206059A1

    公开(公告)日：2023-06-29

    申请号：US17564536

    申请日：2021-12-29

    Applicant: X Development LLC

    Inventor： Sarah Ann Laszlo ,  Lam Thanh Nguyen ,  Baihan Lin

    IPC: G06N3/08 ,  G06N3/063

    CPC classification number: G06N3/08 ,  G06N3/063

    Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus for training a neural network, the method including: obtaining a set of training examples, where each training example includes: (i) a training input, and (ii) a target output, and training the neural network on the set of training examples. Training the neural network can include, for each training example: processing the training input using the neural network to generate a corresponding training output, updating current values of at least a set of encoder sub-network parameters and a set of decoder sub-network parameters by a supervised update, and updating current values of at least a set of brain emulation sub-network parameters by an unsupervised update based on correlations between activation values generated by artificial neurons of the neural network during processing of the training input by the neural network.

    Scalable experimental workflow for parameter estimation
    73.
    发明授权
    Scalable experimental workflow for parameter estimation 有权

    公开(公告)号：US11688487B2

    公开(公告)日：2023-06-27

    申请号：US16527380

    申请日：2019-07-31

    Applicant: X Development LLC

    Inventor： Yu Tanouchi ,  Nicholas Ruggero

    IPC: G16B5/00 ,  G16B40/00 ,  C12M1/34

    CPC classification number: G16B5/00 ,  C12M41/32 ,  C12M41/36 ,  C12M41/46 ,  G16B40/00

    Abstract: The present disclosure relates to a scalable experimental workflow that uses a culture system to maintain a steady state in a biological system, and techniques for identifying values for parameters in a in silico model based on experimental data obtained from the biological system. Particularly, aspects of the present disclosure are directed to obtaining measurement data for one or more characteristics of a biological system developed in a culture system, where the measurement data is indicative of each of the one or more characteristics at a physiological steady state where growth of the biological system is occurring at a substantially constant growth rate, determining a value for a parameter of a model of the biological system based on an growth formula, the measurement data, and the substantially constant growth rate, and parametrizing the model with at least the value determined for the parameter.

    Asynchronous robotic control using most recently selected robotic action data
    74.
    发明授权
    Asynchronous robotic control using most recently selected robotic action data 有权

    公开(公告)号：US11685045B1

    公开(公告)日：2023-06-27

    申请号：US16948187

    申请日：2020-09-08

    Applicant: X Development LLC

    Inventor： Alexander Herzog ,  Dmitry Kalashnikov ,  Julian Ibarz

    IPC: B25J9/16

    CPC classification number: B25J9/161 ,  B25J9/163 ,  B25J9/1661 ,  B25J9/1669 ,  B25J9/1697

    Abstract: Asynchronous robotic control utilizing a trained critic network. During performance of a robotic task based on a sequence of robotic actions determined utilizing the critic network, a corresponding next robotic action of the sequence is determined while a corresponding previous robotic action of the sequence is still being implemented. Optionally, the next robotic action can be fully determined and/or can begin to be implemented before implementation of the previous robotic action is completed. In determining the next robotic action, most recently selected robotic action data is processed using the critic network, where such data conveys information about the previous robotic action that is still being implemented. Some implementations additionally or alternatively relate to determining when to implement a robotic action that is determined in an asynchronous manner.

    ATTENTION-BASED BRAIN EMULATION NEURAL NETWORKS
    75.
    发明公开
    ATTENTION-BASED BRAIN EMULATION NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230196059A1

    公开(公告)日：2023-06-22

    申请号：US17557618

    申请日：2021-12-21

    Applicant: X Development LLC

    Inventor： Sarah Ann Laszlo ,  Lam Thanh Nguyen ,  Baihan Lin ,  Julia Renee Watson ,  Garrett Raymond Honke

    IPC: G06N3/00

    CPC classification number: G06N3/008

    Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus, the method includes: obtaining a network input including a respective data element at each input position in a sequence of input positions, and processing the network input using a neural network to generate a network output that defines a prediction related to the network input, where the neural network includes a sequence of encoder blocks and a decoder block, where each encoder block has a respective set of encoder block parameters, and where the set of encoder block parameters includes multiple brain emulation parameters that, when initialized, represent biological connectivity between multiple biological neuronal elements in a brain of a biological organism.

    MOUNT FOR A CALIBRATION TARGET FOR ULTRASONIC REMOVAL OF ECTOPARASITES FROM FISH
    76.
    发明公开
    MOUNT FOR A CALIBRATION TARGET FOR ULTRASONIC REMOVAL OF ECTOPARASITES FROM FISH 审中-公开

    公开(公告)号：US20230189766A1

    公开(公告)日：2023-06-22

    申请号：US17557891

    申请日：2021-12-21

    Applicant: X Development LLC

    Inventor： Grace Calvert Young ,  Matthew Aaron Knoll ,  Bryce Jason Remesch

    IPC: A01K61/13 ,  G01S5/20

    CPC classification number: A01K61/13 ,  G01S5/20

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for obtaining initial parameters for ultrasonic transducers around a calibration target. The calibration target can include a fish-shaped structure, sensors placed at different locations of the fish-shaped structure, a processor that receives sensor values from the sensors, and a transmitter that outputs sensor data from the calibration target based on the sensor values. The calibration target can be fixed at a particular position relative to the ultrasonic transducers by a filament coupled to both the calibration target and a support structure. Sensor data can be obtained from the calibration target at the particular position relative to the ultrasonic transducers, and relative locations of the sensors can be determined. Parameters for the ultrasonic transducers around the calibration target can be adjusted based on the sensor data and the respective locations of the sensors.

    NEURAL NETWORKS BASED ON HYBRIDIZED SYNAPTIC CONNECTIVITY GRAPHS
    78.
    发明公开
    NEURAL NETWORKS BASED ON HYBRIDIZED SYNAPTIC CONNECTIVITY GRAPHS 审中-公开

    公开(公告)号：US20230186059A1

    公开(公告)日：2023-06-15

    申请号：US17547107

    申请日：2021-12-09

    Applicant: X Development LLC

    Inventor： Sarah Ann Laszlo ,  Estefany Kelly Buchanan ,  Baihan Lin

    IPC: G06N3/06 ,  G06N3/04

    CPC classification number: G06N3/061 ,  G06N3/0472

    Abstract: In one aspect, there is provided a method performed by one or more data processing apparatus that includes obtaining a network input and processing the network input using a neural network to generate a network output that defines a prediction for the network input. The method further includes processing the network input using an encoding sub-network of the neural network to generate an embedding of the network input, processing the embedding of the network input using a brain hybridization sub-network of the neural network to generate an alternative embedding of the network input, and processing the alternative embedding of the network input using a decoding sub-network of the neural network to generate the network output that defines the prediction for the network input.

    IONIC LIQUID-BASED DEPOLYMERIZATION OPTIMIZATION
    80.
    发明公开
    IONIC LIQUID-BASED DEPOLYMERIZATION OPTIMIZATION 审中-公开

    公开(公告)号：US20230170056A1

    公开(公告)日：2023-06-01

    申请号：US17967711

    申请日：2022-10-17

    Applicant: X Development LLC

    Inventor： Julia Yang ,  Vahe Gharakhanyan ,  Tusharkumar Gadhiya ,  Alexander Holiday

    IPC: G16C20/10 ,  G16C60/00 ,  C08J11/10

    CPC classification number: G16C20/10 ,  G16C60/00 ,  C08J11/10

    Abstract: Methods may include accessing a first data set that includes a plurality of first data elements. Each of the plurality of first data elements may characterize a depolymerization reaction. Each first data element may include an embedded representation of a structure of a reactant and a reaction-characteristic value that characterizes a reaction between the reactant and a polymer. The embedded representation may be identified as a set of coordinate values within an embedding space. The method may include constructing a predictive function to predict reaction-characteristic values from embedded representations. The method may also include evaluating a utility function that transforms a given point within the embedding space into a utility metric. The method may include identifying particular points as corresponding to high utility metrics. The method may also include outputting a result that identifies a reactant corresponding to the particular point or a reactant structure corresponding to the particular point.

Patent Agency Ranking