Exploring Se4ai Model Quality
Exploring Se4ai Model Quality reveals several interesting facts.
- Sixth lecture of the Carnegie Mellon course "17-445/645 Software Engineering for AI-Enabled Systems", Summer 2020 Discusses ...
- Beyond data and
- Discussing security principles in general and ML-specific attacks (poisoning attacks, evasion attacks) and counter strategies both ...
- Discussing safety of systems with an ML component, classic safety strategies (requirements, hazard analysis, system design), ...
- Fairness is a challenge, but we can actually do many things: Measures of fairness and how they correspond to different goals and ...
In-Depth Information on Se4ai Model Quality
4th lecture of the Carnegie Mellon course "17-445/645 Software Engineering for AI-Enabled Systems", Summer 2020 Discusses ... About the ultimate heldout test data: production data. Covers measuring About various kinds of data ... Summer 2020 Catches up on some more
Short lecture after Molham's invited talk, catching up on data programming with Snorkel and briefly discussing challenges of ...
Stay tuned for more updates related to Se4ai Model Quality.
