01 / evaluation
All of that process gets done in milliseconds because we use a lot of caching, we've trained the models offline, then the inference happens at real time in really low latency.
“All of that process gets done in milliseconds because we use a lot of caching, we've trained the models offline, then the inference happens at real time in really low latency.”
- Speaker
- Diarmuid Gill
- Episode
- Milliseconds to Match: Criteo's AdTech AI & the Future of Commerce w/ Diarmuid Gill & Liva Ralaivola
- Publisher
- The Cognitive Revolution