利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

1433 条记录 (耗时 0.029 秒)

    Generation of virtual training sets for neural net applications
    84.
    发明授权
    Generation of virtual training sets for neural net applications 有权

    公开(公告)号：US11954176B1

    公开(公告)日：2024-04-09

    申请号：US18308503

    申请日：2023-04-27

    申请人： Periculum Labs Inc.

    发明人： Stephen W. Eisenhawer ,  Terry F. Bott

    IPC分类号： G06N5/04 ,  G06F18/214 ,  G06N3/084 ,  G06N7/01

    CPC分类号： G06F18/2148 ,  G06N3/084 ,  G06N5/04 ,  G06N7/01

    摘要： One embodiment of the present invention provides a computer implemented method for generating a training set to train a convolutional neural network comprising the steps of providing prediction space data to a General Logic Gate Module (GLGM). Prediction space expert judgement is also provided to the GLGM and to a sensitivity and importance module. The GLGM determines or outputs state possibilities. The state possibilities are provided to the sensitivity and importance module and to the feature extraction module. Feature extraction algorithms are applied to the state possibilities within the feature extraction module to produce a training possibility set that is a virtual training possibility set. The training possibility set is provided to a state inferential module and to a final training set. From the state inferential module a possibility ranking is generated that is independent of the convolutional neural network and further the output from the state inferential module is provided to a sensitivity and importance module for analysis. A sensitivity parameter and an importance parameter is determined from the output from the sensitivity and importance module. The state possibility ranking is provided to the final training set. The sensitivity parameter and importance parameter are provided to a final training set and a training set structure metric. A convolutional neural network input layer is generated from the final training set informed by one or more of the state possibility ranking, the sensitivity parameter, the importance parameter and the training possibility set. A convolutional neural network layer design is generated from the training set structure metric.

    Discovering and resolving training conflicts in machine learning systems
    87.
    发明授权
    Discovering and resolving training conflicts in machine learning systems 有权

    公开(公告)号：US11941493B2

    公开(公告)日：2024-03-26

    申请号：US16287224

    申请日：2019-02-27

    申请人： International Business Machines Corporation

    发明人： Michael Desmond ,  Matthew R. Arnold ,  Jeffrey S. Boston

    IPC分类号： G06N20/00 ,  G06N3/08 ,  G06N7/01

    CPC分类号： G06N20/00 ,  G06N3/08 ,  G06N7/01

    摘要： A method optimizes a training of a machine learning system. A conflict detection system discovers a conflict between a first training data and a second training data for a machine learning system, where the first training data and the second training data are ground truths that describe a same type of entity, and where the first training data and the second training data have different labels. In response to discovering the conflict between the first training data and the second training data for the machine learning system, an oracle adjusts the different labels of the first training data and the second training data. The machine learning system is then trained using the first training data and the second training data with the adjusted labels.