
基本信息:
- 专利标题: 人工神经网络调整方法和装置
- 专利标题(英):Artificial neural network adjustment method and device
- 申请号:CN201810608259.2 申请日:2018-06-13
- 公开(公告)号:CN110598723A 公开(公告)日:2019-12-20
- 发明人: 高梓桁
- 申请人: 北京深鉴智能科技有限公司
- 申请人地址: 北京市海淀区王庄路1号院四号楼17层1706号
- 专利权人: 北京深鉴智能科技有限公司
- 当前专利权人: 赛灵思电子科技(北京)有限公司
- 当前专利权人地址: 北京市海淀区王庄路1号院四号楼17层1706号
- 代理机构: 北京展翼知识产权代理事务所
- 代理人: 张阳
- 主分类号: G06K9/62
- IPC分类号: G06K9/62
The invention provides an ANN (artificial neural network) adjustment method and device; the last full connection layer of the ANN is a classifier for classification, and the normalized weight of the layer represents various feature centers, and the method comprises the following steps: adjusting the ANN by using a first loss function for constraining an included angle of the feature centers; and completing the training of the ANN under the condition that the included angle distribution of each feature center tends to be uniform. According to the method, the angles of the feature centers are constrained by using the loss function, so that the included angles between the feature centers can be more uniform, and the problem of adverse effects on a classification result due to insufficient distinction degree of intra-class deviation and inter-class deviation can be well solved.
公开/授权文献:
- CN110598723B 人工神经网络调整方法和装置 公开/授权日:2023-12-12
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 |
--------G06K9/62 | .应用电子设备进行识别的方法或装置 |