Invention Application
US20150278628A1 INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS
审中-公开
使用SPIKING神经网络的图像的不确定对象表示
- Patent Title: INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS
- Patent Title (中): 使用SPIKING神经网络的图像的不确定对象表示
-
Application No.: US14228071Application Date: 2014-03-27
-
Publication No.: US20150278628A1Publication Date: 2015-10-01
- Inventor: Pulkit AGRAWAL , Somdeb MAJUMDAR , Vikram GUPTA
- Applicant: QUALCOMM Incorporated
- Applicant Address: US CA San Diego
- Assignee: QUALCOMM Incorporated
- Current Assignee: QUALCOMM Incorporated
- Current Assignee Address: US CA San Diego
- Main IPC: G06K9/46
- IPC: G06K9/46 ; G06K9/66
Abstract:
A method for generating a histogram in a spiking neural network includes counting spikes associated with a latency encoded representation of an object. The method also includes generating the histogram based on the spike count.
Information query
