GiskardHow to test ML Models? (3/n): numerical data driftWasserstein metrics, Earthmover distance, Kolmogorov test… Drift for numerical features in Machine Learning can be tested using many…4 min read·Apr 20, 2022----
GiskardHow to test ML Models? (2/n): categorical data driftKullback-Leibler (KL) divergence, Population stability index (PSI), Chi-square, etc. Drifts for categorical data in Machine Learning can be…5 min read·Mar 31, 2022--1--1
Giskard🧪 How to test ML models? (1/n)While regulators are asking for Quality management systems for AI (article 17 from the European AI Act), the capacity to create tests is…2 min read·Mar 24, 2022----
Giskard🔍 Where do biases in ML come from? (7/N): 👀 PresentationIn this post, we focus on presentation bias, a negative effect present in almost all ML systems with User Interfaces (UI).3 min read·Jan 14, 2022----
Giskard🔍 Where do biases in #AI / #ML come from? (6/N): Emergent biasIn this post, we focus on emergent bias among the most commonplace biases in AI.3 min read·Jan 7, 2022----
GiskardWishing y’all a happy & healthy 2022! 🎊2021 has been an eventful & productive year 🚀1 min read·Jan 3, 2022----
Giskard🔍 Where do biases in ML come from? (5/N) 📊 Structural biasIn this post, we focus on structural biases 🕵️♂️2 min read·Dec 14, 2021----
Giskard🔍 Where do biases in ML come from? (4/N) 📊 SelectionIn this post, we focus on selection biases. 📊2 min read·Dec 10, 2021----
Giskard🔍 Where do biases in ML come from? (3/N) 📏 MeasurementIn this post, we focus on one of the most important biases: measurement 📏2 min read·Dec 10, 2021----
Giskard🔍 Where do biases in ML come from? (2/N) ❌ ExclusionIn this second post about the reasons for biases in ML, we focus on one of the most important biases in ML: exclusion biases. ⚠2 min read·Dec 10, 2021----