Evelina Gabasova
where else to find them
what they talk about
all 7 in the filters
where they keep going back
- NDC London3 editions2017–2020
- NDC Oslo2 editions2016–2018
- Lambda Days2 editions2016–2018
all 11 in the filters
on a stage with
- Barbara Fusinskaonce
- Jennifer Marsmanonce
who talks about the same things
- Tess Ferrandez-Norlander24 talks
- Scott Hanselman90 talks
- Tomas Petricek22 talks
- Vincent D Warmerdam22 talks
- Aileen Nielsen7 talks
- Ian Ozsvald17 talks
| title | conference | date |
|---|---|---|
| Breaking black-box AI | NDC London 2020 | 2020-01-27 |
Demos run with R, scikit‑learn and Microsoft Cognitive Services expose concrete failures: R linear regression: one outlier raises R² from ~2.5% to 98% and… | ||
| Breaking black-box AI | Code Mesh LDN 2019 | 2019-11-07 |
Live demos use scikit-learn, TensorFlow and Azure Cognitive Services to show concrete failures: a single outlier turns a random dataset into a model with R² ≈… | ||
| Breaking Black-Box AI | DevConf 2019 | 2019-09-25 |
Uses R and scikit-learn to show concrete failures: adding one outlier at (100,100) turns a 90% p-value random fit into a model with 98% R‑squared, a single… | ||
| "Breaking black-box machine learning" | Build Stuff Spain 2019 | 2019-05-23 |
Shows concrete failures and tools: uses R linear regression, scikit-learn decision trees, F# and Microsoft Cognitive Services vision API on real datasets (bike… | ||
| Tabs, spaces and salaries: a data science detective story | NDC Porto 2019 | 2019-02-26 |
Stack Overflow’s claim that developers who use spaces earn more is reproduced from the survey but investigation shows why: a regressed model (full vs reduced)… | ||
| Tabs, spaces and salaries: a data science detective story | NDC London 2019 | 2019-01-30 |
Stack Overflow survey shows developers who report using spaces have higher median pay, but analysis uses linear regression on thousands of responses and finds… | ||
| A developer's guide to probabilistic programming | Lambda World Seattle 2018 | 2018-09-17 |
Uses F# computation expressions and CSV type providers to turn probabilistic models into first-class code, builds a toy inference engine that does complete… | ||
| Tabs, spaces and salaries: a data science detective story | NDC Oslo 2018 | 2018-06-11 |
Analysis of the Stack Overflow developer survey shows developers who report using spaces have about a $10,000 difference in median salary across experience… | ||
| How to look like a statistician (...) | Lambda Days 2018 | 2018-02-22 |
Claim: developers can write Bayesian models without a PhD and let an engine do the heavy lifting. Uses F# prototypes and Stan, implements sampling and a brute… | ||
| The mysterious correlation: a detective story | Codemotion Milan 2017 | 2017-11-10 |
Stack Overflow survey shows spaces associated with higher median salary but deeper analysis using linear models finds linear regression and adjusted R^2 equal… | ||
| .NET Rocks Live Panel on Machine Learning | NDC London 2017 | 2017-01-16 |
Join Carl and Richard from .NET Rocks and a panel including Jennifer Marsman, Barbara Fusinska and Evelina Gabasova discussing the state of machine learning… | ||
| Exploring StackOverflow data | NDC London 2017 | 2017-01-16 |
Whole StackOverflow XML dump (~100–135 GB) is preprocessed into a ~1.5 GB CSV and analyzed with CSV type provider in F#; a weekend index compares weekend vs… | ||
| Exploring StackOverflow Data | GOTO Copenhagen 2016 | 2016-10-03 |
Stack Overflow’s quarterly dump (≈135 GB, ~5M users, ~1M with fillable locations) gets parsed with type providers (CSV, JSON, HTML) to infer schema and call… | ||
| The F#orce Awakens | NDC Oslo 2016 | 2016-06-08 |
Parses seven Star Wars screenplays with active patterns in F#, resolves OCR name quirks, and augments missing silent characters (R2‑D2, Chewbacca) by scaling… | ||
| The F#orce Awakens | Lambda Days 2016 | 2016-02-25 |
Parses movie scripts with the F# Data HTML type provider and active patterns, patches missing speech by estimating counts for non-speaking characters like… | ||
| How machine learning helps cancer research | Strange Loop 2015 | 2015-09-24 |
Machine learning identifies concrete results: clustering of gene-expression to find cancer subtypes that correlate with treatment response and survival; matrix… | ||
| nothing matches | ||