Feature extraction using multi-task learning

    公开(公告)号:GB2580855A

    公开(公告)日:2020-07-29

    申请号:GB202008897

    申请日:2018-08-24

    Applicant: IBM

    Abstract: Systems and methods training a model are disclosed. In the method, training data is obtained by a deep neural network (DNN) first, the deep neural network comprising at least one hidden layer. Then features of the training data are obtained from a specified hidden layer of the at least one hidden layer, the specified hidden layer being connected respectively to a supervised classification network for classification tasks and an autoencoder based reconstruction network for reconstruction tasks. And at last the DNN, the supervised classification network and the reconstruction network are trained as a whole based on the obtained features, the training being guided by the classification tasks and the reconstruction tasks

    Intelligent in-vehicle air-quality control

    公开(公告)号:GB2575214A

    公开(公告)日:2020-01-01

    申请号:GB201915229

    申请日:2018-01-23

    Applicant: IBM

    Abstract: A computer-implemented method and a computer program product and apparatus are provided for controlling the internal air-quality of a vehicle. In-vehicle sensor data of a vehicle are acquired and the usage status of the vehicle is determined based on the acquired in-vehicle sensor data. Based on the acquired in-vehicle sensor data and the determined usage status, a changing trend of the in-vehicle air-quality is determined and responsive to the determined changing trend of the in-vehicle air-quality, a control system of the vehicle is signaled to control the usage status of the vehicle based on a control policy.

Patent Agency Ranking