- 专利标题: Systems and methods for generating data explanations for neural networks and related systems
-
申请号: US14822730申请日: 2015-08-10
-
公开(公告)号: US10275705B2公开(公告)日: 2019-04-30
- 发明人: Dileep George , Kenneth Alan Kansky , Christopher Remmert Laan , Wolfang Lehrach , Bhaskara Mannar Marthi , David Scott Phoenix , Eric Purdy
- 申请人: Vicarious FPC, Inc.
- 申请人地址: US CA Union City
- 专利权人: Vicarious FPC, Inc.
- 当前专利权人: Vicarious FPC, Inc.
- 当前专利权人地址: US CA Union City
- 代理商 Jeffrey Schox; Thomas Gwinn
- 主分类号: G06N3/04
- IPC分类号: G06N3/04 ; G06K9/62
摘要:
A method for generating data explanations in a recursive cortical network includes receiving a set of evidence data at child feature nodes of a first layer of the recursive cortical network, setting a transformation configuration that directs messaging of evidence data and transformed data between layers of the network, performing a series of transformations on the evidence data according to the transformation configuration, the series including at least one forward transformation and at least one reverse transformation, and outputting the transformed evidence data.
公开/授权文献
信息查询