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

Inventor： WEISHAN DONG ,  TING YUAN ,  KAI YANG ,  CHANGSHENG LI ,  JUN ZHU ,  RENJIE YAO ,  PENG GAO ,  CHUNYANG MA

IPC: G06N3/04

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