Invention Grant
- Patent Title: Scheduling predictive models for machine learning systems
-
Application No.: US14591079Application Date: 2015-01-07
-
Publication No.: US09794145B2Publication Date: 2017-10-17
- Inventor: Jean-Philippe Vasseur , Sukrit Dasgupta , Grégory Mermoud
- Applicant: Cisco Technology, Inc.
- Applicant Address: US CA San Jose
- Assignee: Cisco Technology, Inc.
- Current Assignee: Cisco Technology, Inc.
- Current Assignee Address: US CA San Jose
- Agency: Parker Ibrahim & Berg LLC
- Agent James M. Behmke; Stephen D. LeBarron
- Main IPC: H04L12/26
- IPC: H04L12/26 ; H04L12/24

Abstract:
In one embodiment, a device in a network monitors performance data for a first predictive model. The first predictive model is used to make proactive decisions in the network. The device maintains a supervisory model based on the monitored performance data for the first predictive model. The device identifies a time period during which the supervisory model predicts that the first predictive model will perform poorly. The device causes a switchover from the first predictive model to a second predictive model at a point in time associated with the time period, in response to identifying the time period.
Public/Granted literature
- US20160028599A1 SCHEDULING PREDICTIVE MODELS FOR MACHINE LEARNING SYSTEMS Public/Granted day:2016-01-28
Information query