Invention Grant
- Patent Title: Security system using a convolutional neural network with pruned filters
-
Application No.: US15590666Application Date: 2017-05-09
-
Publication No.: US10885437B2Publication Date: 2021-01-05
- Inventor: Asim Kadav , Igor Durdanovic , Hans Peter Graf , Hao Li
- Applicant: NEC Laboratories America, Inc.
- Applicant Address: US NJ Princeton
- Assignee: NEC Laboratories America, Inc.
- Current Assignee: NEC Laboratories America, Inc.
- Current Assignee Address: US NJ Princeton
- Agent Joseph Kolodka
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08 ; G06K9/62 ; G06K9/00 ; G06K9/46 ; G08B13/00 ; G08B29/18 ; G06F17/15 ; G06F17/17 ; G06K9/66 ; G06N5/04

Abstract:
Security systems and methods for detecting intrusion events include one or more sensors configured to monitor an environment. A pruned convolutional neural network (CNN) is configured process information from the one or more sensors to classify events in the monitored environment. CNN filters having the smallest summed weights have been pruned from the pruned CNN. An alert module is configured to detect an intrusion event in the monitored environment based on event classifications. A control module is configured to perform a security action based on the detection of an intrusion event.
Public/Granted literature
- US20170337467A1 SECURITY SYSTEM USING A CONVOLUTIONAL NEURAL NETWORK WITH PRUNED FILTERS Public/Granted day:2017-11-23
Information query