发明名称 CONVOLUTIONAL NEURAL NETWORK WITH TREE POOLING AND TREE FEATURE MAP SELECTION
摘要 In one aspect, there is provided a method for training a convolutional neural network. The method may include: receiving training data; utilizing the training data to train a convolutional neural network comprising a tree pooling layer, wherein the tree pooling layer applies a soft decision tree to generate one or more pooled feature map; providing a trained convolutional neural network comprising a tree pooling layer. Related systems, methods, and articles of manufacture are also disclosed.
申请公布号 WO2016141282(A1) 申请公布日期 2016.09.09
申请号 WO2016US20869 申请日期 2016.03.04
申请人 THE REGENTS OF THE UNIVERSITY OF CALIFORNIA 发明人 TU, Zhuowen;LEE, Chen-yu
分类号 G06K9/00;G06K9/62;G06T17/00;G10L15/26 主分类号 G06K9/00
代理机构 代理人
主权项
地址