8 papers
Teaching Machine Learning Fundamentals with LEGO Robotics
Viacheslav Sydora, Guner Dilsad Er, Michael Muehlebach
This paper presents the web-based platform Machine Learning with Bricks and an accompanying two-day course designed to teach machine learning concepts to students aged 12 to 17 thr…
A Systems-Theoretic View on the Convergence of Algorithms under Disturbances
Guner Dilsad Er, Sebastian Trimpe, Michael Muehlebach
Algorithms increasingly operate within complex physical, social, and engineering systems where they are exposed to disturbances, noise, and interconnections with other dynamical sy…
A Critical Perspective on Finite Sample Conformal Prediction Theory in Medical Applications
Klaus-Rudolf Kladny, Bernhard Schölkopf, Lisa Koch +2
Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (C…
ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining
Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach
Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Model…
Adversarial Training for Defense Against Label Poisoning Attacks
Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach
As machine learning models grow in complexity and increasingly rely on publicly sourced data, such as the human-annotated labels used in training large language models, they become…
Controlling Participation in Federated Learning with Feedback
Michael Cummins, Guner Dilsad Er, Michael Muehlebach
We address the problem of client participation in federated learning, where traditional methods typically rely on a random selection of a small subset of clients for each training…
Bi-Level Motion Imitation for Humanoid Robots
Wenshuai Zhao, Yi Zhao, Joni Pajarinen +1
Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of j…
Conformal Performance Range Prediction for Segmentation Output Quality Control
Anna M. Wundram, Paul Fischer, Michael Muehlebach +2
Recent works have introduced methods to estimate segmentation performance without ground truth, relying solely on neural network softmax outputs. These techniques hold potential fo…