Marianna Diachuk
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
- Build Stuff2 editions2020–2021
all 4 in the filters
on a stage with
- Henk Boelmanonce
- Håkan Silfvernagelonce
- Matthew Renzeonce
all 4 in the filters
who talks about the same things
- Alessandra Bilardi5 talks
- Antje Barth9 talks
- Joshua Arvin Lat20 talks
- Alejandro Saucedo33 talks
- Animesh Singh23 talks
- Julien Simon14 talks
| title | conference | date |
|---|---|---|
| Deploying ML models and all the things that go wrong | Build Stuff 2021 | 2021-11-17 |
Deployment experience since 2017 shows concrete pitfalls: a brittle custom prediction service ends up hosting 20+ models on an unscalable architecture, causing… | ||
| Alice and Mad Hatter.... | Scale By the Bay 2021 | 2021-10-28 |
Built a Scala Spark pipeline that turns raw records into cached RDD vectors, applies RDD vector normalization (mean/stddev), trains KMeans (rerunning to avoid… | ||
| intro video | Scale By the Bay 2021 | 2021-10-28 |
Conference intro previews a case study that builds a prediction pipeline around a narrative called Alice and the Mad Hatter, contrasts a data scientist… | ||
| Deploying ML Models and the Things That Go Wrong | Conf42 Machine Learning 2021 | 2021-07-29 |
Hands-on account of deploying models since 2017 with concrete tradeoffs: choosing dedicated deployment engineers versus expecting data scientists to own… | ||
| AI is everywhere! | Build Stuff 2020 | 2020-11-11 |
Panelists give concrete guidance: take the Johns Hopkins Data Science Specialization or courses on deeplearning.ai, use Kaggle to practice, and prefer API… | ||
| Applying deployment oriented mindset for building Machine Learning models | Data Science fwdays'19 | 2019-09-07 |
Claims hands‑on experience building two deployment services and improving their architecture, with concrete tools and fixes: use of SageMaker… | ||
| nothing matches | ||