公开(公告)号：US11645508B2

公开(公告)日：2023-05-09

申请号：US16002614

申请日：2018-06-07

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sungju Hwang ,  Haebum Lee ,  Donghyun Na ,  Eunho Yang

IPC: G06N3/08 ,  G06F17/16 ,  G06N3/04 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06F17/16 ,  G06N3/04 ,  G06N3/045

Abstract: A method for generating a trained model is provided. The method for generating a trained model includes: receiving a learning data; generating an asymmetric multi-task feature network including a parameter matrix of the trained model which permits an asymmetric knowledge transfer between tasks and a feedback matrix for a feedback connection from the tasks to features; computing a parameter matrix of the asymmetric multi-task feature network using the input learning data to minimize a predetermined objective function; and generating an asymmetric multi-task feature trained model using the computed parameter matrix as the parameter of the generated asymmetric multi-task feature network.

公开(公告)号：US11580376B2

公开(公告)日：2023-02-14

申请号：US16002649

申请日：2018-06-07

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sungju Hwang ,  Gunhee Kim ,  Juyong Kim ,  Yookoon Park

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06F17/16 ,  G06N3/063 ,  G06V30/194

Abstract: An electronic apparatus is provided. The electronic apparatus includes: a memory storing a trained model including a plurality of layers; and a processor initializing a parameter matrix and a plurality of split variables of a trained model, calculating a new parameter matrix having a block-diagonal matrix for the plurality of split variables and the trained model to minimize a loss function for the trained model, a weight decay regularization term, and an objective function including a split regularization term defined by the parameter matrix and the plurality of split variables, vertically splitting the plurality of layers according to the group based on the computed split parameters and reconstruct the trained model using the computed new parameter matrix as parameters of the vertically split layers.