中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.016 seconds)

    Controlling a multiphase flow
    3.
    发明授权
    Controlling a multiphase flow 有权

    公开(公告)号：US12152978B2

    公开(公告)日：2024-11-26

    申请号：US17108362

    申请日：2020-12-01

    Applicant: International Business Machines Corporation

    Inventor： Carlos Peña Monferrer ,  Lan Ngoc Hoang ,  Eloisa Bentivegna ,  Mohab Elkaref

    IPC: G01N15/10 ,  G06N3/08 ,  G06T7/00 ,  G06T15/00

    Abstract: In an approach for controlling a multiphase flow configured to create a plurality of particles, a processor obtains images of a plurality of particles in a multiphase flow. A processor provides the images to a neural network adapted to determine a distribution of a spatial property of the plurality of particles from the provided images. A processor determines the distribution of the spatial property of the plurality of particles in the multiphase flow, based on the provided images, using the neural network. A processor controls the multiphase flow based on the determined distribution.

    INTERPRETABILITY OF DECISION MAKING METHODS
    4.
    发明公开
    INTERPRETABILITY OF DECISION MAKING METHODS 审中-公开

    公开(公告)号：US20240211766A1

    公开(公告)日：2024-06-27

    申请号：US18145846

    申请日：2022-12-22

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Lan Ngoc Hoang ,  Alexander Zadorojniy

    IPC: G06N3/092

    CPC classification number: G06N3/092

    Abstract: A method and system of increasing interpretability of decision making methods include a network module providing raw data from an environment to a machine learning (ML) module. In response to the raw data being delivered to the ML module, the ML module generates a trained classifier using the raw data. A pruning module then prunes a plurality of dominant variables, in the sense of being most relevant for the decision made with respect to the classifier, using the trained classifier. The network module then provides the sub-optimal policy to a reinforcement learning (RL) module, where a generated sub-optimal policy is applied to the environment to obtain a dataset by applying the sub-optimal policy and generating a trajectory. The ML module then generates an interpretable set of rules using the generated trajectory.

    CONTROLLING A MULTIPHASE FLOW
    6.
    发明申请
    CONTROLLING A MULTIPHASE FLOW 有权

    公开(公告)号：US20220170840A1

    公开(公告)日：2022-06-02

    申请号：US17108362

    申请日：2020-12-01

    Applicant: International Business Machines Corporation

    Inventor： Carlos Peña Monferrer ,  Lan Ngoc Hoang ,  Eloisa Bentivegna ,  Mohab Elkaref

    IPC: G01N15/10 ,  G06T7/00 ,  G06N3/08 ,  G06T15/00

    Abstract: In an approach for controlling a multiphase flow configured to create a plurality of particles, a processor obtains images of a plurality of particles in a multiphase flow. A processor provides the images to a neural network adapted to determine a distribution of a spatial property of the plurality of particles from the provided images. A processor determines the distribution of the spatial property of the plurality of particles in the multiphase flow, based on the provided images, using the neural network. A processor controls the multiphase flow based on the determined distribution.

    TRAINING POLICY USING DISTRIBUTIONAL REINFORCEMENT LEARNING AND CONDITIONAL VALUE AT RISK
    7.
    发明公开
    TRAINING POLICY USING DISTRIBUTIONAL REINFORCEMENT LEARNING AND CONDITIONAL VALUE AT RISK 审中-公开

    公开(公告)号：US20240330696A1

    公开(公告)日：2024-10-03

    申请号：US18192650

    申请日：2023-03-30

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Takayuki Osogami ,  Lan Ngoc Hoang

    IPC: G06N3/092 ,  G06N3/0455

    CPC classification number: G06N3/092 ,  G06N3/0455

    Abstract: A computer-implemented method for modifying a current policy using reinforcement learning (RL) includes the following operations. A number, corresponding to an inputted sample size, of Markov Decision Processes (MDPs) defining an environment are sampled. For each of the sampled MDPs, behavior data for the current policy is collected, a quantile function of return with the current policy is determined using the collected behavior data, and a current weight is generated by updating a weight for a particular sampled MDP using the quantile function of return for the particular sampled MDP. The policy is modified based upon the weights for each of the sampled MDPs. The current weights are generated by minimizing a conditional value of at risk (CVaR) of a return of the current policy, and the policy is modified to maximize a weighted average of the CVaR of the return with the current weights.

    Generating logically-represented policy for control systems operating based on constrained Markov decision process (CMDP) models
    8.
    发明授权
    Generating logically-represented policy for control systems operating based on constrained Markov decision process (CMDP) models 有权

    公开(公告)号：US12061450B2

    公开(公告)日：2024-08-13

    申请号：US17528486

    申请日：2021-11-17

    Applicant: International Business Machines Corporation

    Inventor： Alexander Zadorojniy ,  Yishai Abraham Feldman ,  Lan Ngoc Hoang

    IPC: G05B17/02 ,  G06N7/01

    CPC classification number: G05B17/02 ,  G06N7/01

    Abstract: A control system, computer program product, and method for generating a logically-represented policy for a control system operating based on a CMDP model are provided. The control system directs the operation of a controlled application system that is subject to a constraint. The method includes receiving, at the control system, data corresponding to control action variables and system state variables relating to the controlled application system, data corresponding to a cost/reward, and data corresponding to the constraint, and automatically training a CMDP model for the operation of the controlled application system based on the received data, where the CMDP model is formulated using dual linear programming, and where the CMDP model includes a policy corresponding to occupation measures that are decision variables of the dual linear programming formulation. The method also includes automatically generating a logically-represented policy for the control system based on the policy of the CMDP model.

    MULTI-AGENT REINFORCEMENT LEARNING PIPELINE ENSEMBLE
    9.
    发明公开
    MULTI-AGENT REINFORCEMENT LEARNING PIPELINE ENSEMBLE 审中-公开

    公开(公告)号：US20230237385A1

    公开(公告)日：2023-07-27

    申请号：US17583522

    申请日：2022-01-25

    Applicant: International Business Machines Corporation

    Inventor： Lan Ngoc Hoang ,  Long Vu

    IPC: G06N20/20

    CPC classification number: G06N20/20

    Abstract: A computer-implemented method for configuring a plurality of machine learning pipelines into a machine learning pipeline ensemble is disclosed. The computer-implemented method includes determining, by a reinforcement learning agent coupled to a machine learning pipeline, performance information of the machine learning pipeline. The computer-implemented method further includes receiving, by the reinforcement learning agent, configuration parameter values of uncoupled machine learning pipelines of the plurality of machine learning pipelines. The computer-implemented method further includes adjusting, by the reinforcement learning agent, configuration parameter values of the machine learning pipeline based on the performance information of the machine learning pipeline and the configuration parameter values of the uncoupled machine learning pipelines.

Patent Agency Ranking