APPARATUS AND METHOD WITH MULTI-TASK NEURAL NETWORK

    公开(公告)号:US20200265307A1

    公开(公告)日:2020-08-20

    申请号:US16691762

    申请日:2019-11-22

    发明人: SungJoo SUH

    IPC分类号: G06N3/08 G06N3/04 G06F16/22

    摘要: Provided is a neural network method and apparatus. The method includes determining a target task with respect to input data, acquiring a second parameter that is prestored to correspond to the target task among first parameters included in a neural network for a plurality of tasks, adapting the neural network to the target task by setting a value of a portion of the first parameters of the neural network to a value of the second parameter, and implementing the adapted neural network with respect to the input data, and may include obtaining an importance matrix for neural network, determining one or more key parameters of the neural network, updating the importance matrix with respect to the determined one or more key parameters, and training the neural network with training data and for a new task using the updated importance matrix.