2019:Technology outreach & innovation/The hurdles of deploying Machine Learning models in production
![]() | This is a Closed submission for Wikimania 2019. It has been reviewed and was not accepted. |
Description[edit | edit source]
Deploying Machine Learning applications in a production environment poses significant hurdles that the movement hasn't been called to address in a consistent and concise manner up to now. Some adhoc solutions exists. This talk is about identifying those issues, spreading knowledge and proposing solutions.
Relationship to the theme[edit | edit source]
This session will address the conference theme — Wikimedia, Free Knowledge and the Sustainable Development Goals — in the following manner:
- 8 - Decent work and economic growth
- 9 - Industry, Innocation and Infrastructure
Session outcomes[edit | edit source]
At the end of the session, the following will have been achieved:
- The major hurdles to deploying machine learning applications in a production environment will be understood by the audience
- Possible solutions to those issues will have been shown and pros and cons discussed
- Developers interested in having machine learning applications deployed in the movement's infrastructure will have a clear understanding of the requirements
Session leader(s)[edit | edit source]
- Alexandros Kosiaris
Contacts[edit | edit source]
- akosiaris@wikimedia.org, IRC: akosiaris
Session type[edit | edit source]
Each Space at Wikimania 2019 will have specific format requests. The program design prioritises submissions which are future-oriented and directly engage the audience. The format of this submission is a:
- Lecture
Requirements[edit | edit source]
The session will work best with these conditions:
- Room:
- Class room or lecture hall.
- Projector and screen
- Audience:
- 30-50.
- Being/wanting to become a developer with an interest in deploying an application into the movement's production environment a plus
- Recording:
- Freely licensed slides, straight forward presentation, no limitations.