知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

37 records (took 0.02 seconds)

    Artificial intelligence transparency
    4.
    发明授权
    Artificial intelligence transparency 有权

    公开(公告)号：US11651276B2

    公开(公告)日：2023-05-16

    申请号：US16669685

    申请日：2019-10-31

    Applicant: International Business Machines Corporation

    Inventor： Stefan Ravizza ,  Andrea Giovannini ,  Patrick Lustenberger ,  Frederik Frank Flöther ,  Thomas Pfeiffer

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: A computer-implemented method for generating a group of representative model cases for a trained machine learning model may be provided. The method comprising determining an input space, determining an initial plurality of model cases, and expanding the initial plurality of model cases by stepwise modifying field values of the records representing the initial plurality of model cases resulting in an exploration set of model cases. Additionally, the method comprises obtaining a model score value for each record of the exploration set of model cases, continuing the expansion of the exploration set of model cases thereby generating a refined model case set, and selecting the records in the refined model case set based on relative record distance values and related model score values between pairs of records, thereby generating the group of representative model cases.

    QUANTUM CIRCUIT VALUATION
    5.
    发明申请
    QUANTUM CIRCUIT VALUATION 有权

    公开(公告)号：US20220237352A1

    公开(公告)日：2022-07-28

    申请号：US17161277

    申请日：2021-01-28

    Applicant: International Business Machines Corporation

    Inventor： Frederik Frank Flöther ,  Robert E. Loredo ,  Shikhar Kwatra ,  Paul R. Bastide

    IPC: G06F30/337 ,  G06N10/00

    Abstract: Systems and techniques that facilitate quantum circuit valuation are provided. In various embodiments, a system can comprise an input component that can access a first quantum circuit. In various embodiments, the system can further comprise a valuation component that can appraise the first quantum circuit based on one or more factors (e.g., frequency factor, complexity factor, resource factor, similarity factor), thereby yielding a value score that characterizes the first quantum circuit. In various instances, the system can further comprise an execution component that can recommend deployment of the first quantum circuit based on determining that the value score exceeds a threshold.

    COGNITIVE GENERATION OF TAILORED ANALOGIES
    8.
    发明申请
    COGNITIVE GENERATION OF TAILORED ANALOGIES 有权

    公开(公告)号：US20220335041A1

    公开(公告)日：2022-10-20

    申请号：US17232387

    申请日：2021-04-16

    Applicant: International Business Machines Corporation

    Inventor： Shikhar Kwatra ,  Robert E. Loredo ,  Frederik Frank Flöther ,  Stefan Ravizza

    IPC: G06F16/245 ,  G06F16/248 ,  G06F16/58 ,  G06F16/28 ,  G06Q30/04 ,  G06K9/62 ,  G10L15/26

    Abstract: An embodiment includes processing a dataset to generate a set of feature vectors that include a first feature vector corresponding to a first concept within a user's areas of interest and a second feature vector corresponding to a second concept within the user's areas of study. The embodiment identifies clusters of the feature vectors and identifies key features that most contribute to influencing the clustering algorithm. The embodiment selects the first feature vector in response to a user query, and then selects the second feature vector based on an overlap between key features of the first and second feature vectors and a degree of dissimilarity between the first and second concepts. The embodiment outputs a query response that includes the second concept. The embodiment also determines an effectiveness value based on sensor data indicative of a user action responsive to the outputting of the response to the query.

    QUANTUM PLATFORM ROUTING OF A QUANTUM APPLICATION COMPONENT
    9.
    发明申请
    QUANTUM PLATFORM ROUTING OF A QUANTUM APPLICATION COMPONENT 有权

    公开(公告)号：US20210097419A1

    公开(公告)日：2021-04-01

    申请号：US16588115

    申请日：2019-09-30

    Applicant: International Business Machines Corporation

    Inventor： Jared Andrew Limberg ,  Frederik Frank Flöther ,  Vinod A. Valecha

    IPC: G06N10/00 ,  G06N20/00

    Abstract: Systems, computer-implemented methods, and computer program products to facilitate quantum platform routing of a quantum application component are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a dissection component that identifies one or more components of a quantum application. The computer executable components can further comprise a determination component that selects at least one quantum platform to execute the one or more components of the quantum application based on a defined run criterion.

    FAIRNESS IMPROVEMENT THROUGH REINFORCEMENT LEARNING
    10.
    发明申请
    FAIRNESS IMPROVEMENT THROUGH REINFORCEMENT LEARNING 审中-公开

    公开(公告)号：US20200320428A1

    公开(公告)日：2020-10-08

    申请号：US16377727

    申请日：2019-04-08

    Applicant: International Business Machines Corporation

    Inventor： Georgios Chaloulos ,  Frederik Frank Flöther ,  Florian Graf ,  Patrick Lustenberger ,  Stefan Ravizza ,  Eric Slottke

    IPC: G06N20/00 ,  G06N3/08

    Abstract: A computer-implemented method for improving fairness in a supervised machine-learning model may be provided. The method comprises linking the supervised machine-learning model to a reinforcement learning meta model, selecting a list of hyper-parameters and parameters of the supervised machine-learning model, and controlling at least one aspect of the supervised machine-learning model by adjusting hyper-parameters values and parameter values of the list of hyper-parameters and parameters of the supervised machine-learning model by a reinforcement learning engine relating to the reinforcement learning meta model by calculating a reward function based on multiple conflicting objective functions. The method further comprises repeating iteratively the steps of selecting and controlling for improving a fairness value of the supervised machine-learning model.

Patent Agency Ranking