基本信息:
- 专利标题： RELEVANCE SCORE ASSIGNMENT FOR ARTIFICIAL NEURAL NETWORK
- 专利标题（中）：人工神经网络的相关性评分
- 申请号：EP15711738.3 申请日：2015-03-20
- 公开(公告)号：EP3271863A1 公开(公告)日：2018-01-24
- 发明人： LAPUSCHKIN, Sebastian , SAMEK, Wojciech , MÜLLER, Klaus-Robert , BINDER, Alexander , MONTAVON, Grégoire
- 申请人： Fraunhofer Gesellschaft zur Förderung der angewandten Forschung E.V. , Technische Universität Berlin
- 申请人地址： Hansastrasse 27C 80686 München DE
- 专利权人： Fraunhofer Gesellschaft zur Förderung der angewandten Forschung E.V.,Technische Universität Berlin
- 当前专利权人： FRAUNHOFER-GESELLSCHAFT ZUR FOERDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
- 当前专利权人地址： FRAUNHOFER-GESELLSCHAFT ZUR FOERDERUNG DER ANGEWANDTEN FORSCHUNG E.V.
- 代理机构： Zimmermann, Tankred Klaus
- 国际公布： WO2016150472 20160929
- 主分类号： G06K9/00
- IPC分类号： G06K9/00 ; G06T1/20 ; G06N3/04 ; G06N3/08
摘要：
The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.
公开/授权文献:
- EP3271863B1 RELEVANCE SCORE ASSIGNMENT FOR ARTIFICIAL NEURAL NETWORK 公开/授权日：2021-07-28
IPC结构图谱:
| G | 物理 |
| --G06 | 计算；推算；计数 |
| ----G06K | 数据识别；数据表示；记录载体；记录载体的处理 |
| ------G06K9/00 | 用于阅读或识别印刷或书写字符或者用于识别图形，例如，指纹的方法或装置 |