- 专利标题： LEARNING METHOD BASED ON DEEP LEARNING MODEL HAVING NON-CONSECUTIVE STOCHASTIC NEURON AND KNOWLEDGE TRANSFER, AND SYSTEM THEREOF
-
申请号： US15365641申请日： 2016-11-30
-
公开(公告)号： US20180129930A1公开(公告)日： 2018-05-10
- 发明人: Jinwoo Shin , Song Chong , Kimin Lee
- 申请人： Korea Advanced Institute of Science and Technology
- 申请人地址： KR Daejeon
- 专利权人： Korea Advanced Institute of Science and Technology
- 当前专利权人： Korea Advanced Institute of Science and Technology
- 当前专利权人地址： KR Daejeon
- 优先权： KR10-2016-0147329 20161107
- 主分类号： G06N3/04
- IPC分类号： G06N3/04 ; G06N3/08
摘要：
Disclosed is a learning method based on a stochastic-based deep learning model having a non-consecutive stochastic neural. The learning method includes configuring a non-consecutive stochastic feedforward neural network (NCSFNN) having non-consecutive stochastic neuron as a leaning model including a plurality of hidden layers; and allowing the NCSFNN to learn.
信息查询
