Neural network learning method and device

    公开(公告)号:US11586923B2

    公开(公告)日:2023-02-21

    申请号:US16645158

    申请日:2018-09-06

    Abstract: The disclosure relates to an artificial intelligence (AI) system for mimicking functions, such as cognition and determination as of the human brain, by utilizing a machine learning algorithm such as deep learning, and an application thereof. Provided are a neural network learning method according to an AI system and applications thereof, the method including extracting, by using a masking filter having an effective value in a specific portion of the masking filter including weight information of at least one hidden layer included in a learning network model, characteristics of input data according to weight information of a filter corresponding to the specific portion, comparing output data with target data, the output data being obtained from the learning network model based on extracted characteristics of the input data, and updating a size of the specific portion having the effective value in the masking filter, based on a result of the comparing.

    Single-shot pseudo-centric epi method for magnetization-prepared imaging

    公开(公告)号:US11573283B1

    公开(公告)日:2023-02-07

    申请号:US17380604

    申请日:2021-07-20

    Abstract: Provided is a method for generating MRI data including applying, by an MRI computing device, an RF excitation pulse, and completing, by the MRI computing device, a K-space by acquiring a plurality of phase encoding line groups, in a state in which any other RF excitation pulse is not applied after applying the RF excitation pulse, in which each of the plurality of phase encoding line groups includes a plurality of phase encoding lines, and an absolute value of an average phase encoding size of a phase encoding line group acquired earlier is not greater than an absolute value of an average phase encoding size of a phase encoding line group acquired later, among the plurality of phase encoding line groups.

Patent Agency Ranking