Valdas Druskinis
Valdas is a Machine Learning Engineer at carVertical, where he builds reliable and interpretable ML systems with a strong focus on end-to-end model and data lifecycles. Previously, he has lived and worked in multiple countries, including time at Mercedes-Benz AG, and has built production systems across classical ML, deep learning, and GenAI.
Session
04-09
14:00
25min
Beyond SHAP: Diagnosing Vector Embeddings with Visual Explainable AI
Valdas Druskinis
When your embedding-based classification model fails, should you collect more data or try a different approach? This talk shares a practical XAI workflow using UMAP visualization and prototype analysis to uncover systematic failures. We will explore how to use these tools to identify semantic overlaps and make evidence-based decisions when debugging high-dimensional similarity systems.
Data Day - Apr 9
Deimantas/Diamond (3rd building)