| 发明名称 |
INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS |
| 摘要 |
A method for invariantly representing an object using a spiking neural network includes representing the object by a spike sequence. The method also includes determining a reference feature of the object representation. The method further includes transforming the object representation to a canonical form based on the reference feature. |
| 申请公布号 |
US2015278641(A1) |
申请公布日期 |
2015.10.01 |
| 申请号 |
US201414228065 |
申请日期 |
2014.03.27 |
| 申请人 |
QUALCOMM Incorporated |
发明人 |
AGRAWAL Pulkit;MAJUMDAR Somdeb |
| 分类号 |
G06K9/66;G06K9/68;G06K9/46 |
主分类号 |
G06K9/66 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A method for invariantly representing an object using a spiking neural network, comprising:
representing the object by a spike sequence; determining a reference feature of the object representation; and transforming the object representation to a canonical form based at least in part on the reference feature. |
| 地址 |
San Diego CA US |
