Scheduling predictive models for machine learning systems
US9794145B2 · kind B2 · utility
11Cited by
8References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 7, 2015 |
| Grant date | Oct 17, 2017 |
| Priority date | — |
| Expiry date | Jun 18, 2035 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L41/149
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.