Data Models for Dataset Drift Controls in Machine Learning With Optical Images

Luis Oala, Marco Aversa, Gabriel Nobis, Kurt Willis, Yoan Neuenschwander, Michèle Buck, Christian Matek, Jerome Extermann, Enrico Pomarico, Wojciech Samek, Roderick Murray-Smith, Christoph Clausen, Bruno Sanguinetti

Keywords: data drift, data models

TL;DR: Differentiable data models of images allow novel, physically faithful controls for data drift

Abstract:

This study addresses robustness concerns in machine learning due to dataset drift by integrating physical optics with machine learning to create explicit, differentiable data models. These models illuminate the impact of data generation on model performance and facilitate drift synthesis, precise tolerancing of model sensitivity (drift forensics), and beneficial drift creation (drift optimization). Accompanying the study are two datasets, Raw-Microscopy and Raw-Drone, available at https://github.com/aiaudit-org/raw2logit.

*Note:* The full-length archival version of this manuscript can be found in the *Transactions on Machine Learning Research* (TMLR) at https://openreview.net/forum?id=I4IkGmgFJz.

Submission Number: 25