Name of the submitter: Sridhar K. N. Rao and Lei Huang
Affiliation: LF/LFN/LFN-Anuket/Anuket-Thoth (CM is interested in this problem, and the exact participation scope is yet to be decided)
ITU AI for Good Initiative.
Who will be the host? - LFN-Anuket. Anuket-Thoth should be the host.
Anuket Thoth.
Host: Anuket-Thoth and China Mobile LF-AI (https://wiki.lfaidata.foundation/display/ADLIK/2020+DNN+Inference+Optimization+Challenge)
Contact email: sridharkn@u.nus.edu and huangleiyjy@chinamobile.com
Country: India and China.
Title of problem statement: Synthetic Observability Data Generation using GANs.
...
Would you offer prizes or incentives for winners of this problem statement? : YES. In Consideration
| Category | Details |
|---|---|
| Id | ITU-ML5G-PS-SODGANS**-***** |
| Title | Synthetic Observability Data Generation using GANs |
| Description | Observability data can be any of the following:
Availability of these data for AI/ML researchers, who are not part of the Telco, is very difficult. To solve this availability issue, one approach is to generate synthetic observability data. In this project, we propose to generate this synthetic observability data using GANs. For this first round only Telco-Cloud Infrastructure Metrics will be considered. |
| Evaluation criteria |
|
| Data source | Real-World observability data (Telco-Cloud Infrastructure Metrics) will be provided |
| Resources | Computing resources can be provided to those who do not have access to one. |
| Any controls or restrictions | Anything around data, use of the models. |
| Specification/Paper reference | |
| Contact | Sridhar K. N. Rao Lei Huang |
Next Steps:
- Submit the above filled template to Thomas (ITU).
- ITU will make it publicly available on the registration platform,
- Introduction Talk - by Sridhar. Tentative date: 22-06-22. (25 or 27)
- Submit the abstract of the talk (including Bio, Pic), 2 weeks before.
- Dataset - ITU Platform (if its up to 1 or 2gb) or Github.
...