collaborators

6 papers

cs.LG2025

Data Augmentation of Time-Series Data in Human Movement Biomechanics: A Scoping Review

Christina Halmich, Lucas Höschler, Christoph Schranz +1

The integration of machine learning and deep learning has transformed data analytics in biomechanics, enabled by extensive wearable sensor data. However, the field faces challenges…

cs.LG2024

Convolutional Differentiable Logic Gate Networks

Felix Petersen, Hilde Kuehne, Christian Borgelt +2

With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gat…

cs.LG2024

TrAct: Making First-layer Pre-Activations Trainable

Felix Petersen, Christian Borgelt, Stefano Ermon

We consider the training of the first layer of vision models and notice the clear relationship between pixel values and gradient update magnitudes: the gradients arriving at the we…

cs.LG2024

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

Felix Petersen, Christian Borgelt, Tobias Sutter +3

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular appr…

cs.LG2024

Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation

Felix Petersen, Christian Borgelt, Aashwin Mishra +1

We deal with the problem of gradient estimation for stochastic differentiable relaxations of algorithms, operators, simulators, and other non-differentiable functions. Stochastic s…

cs.LG2024

Uncertainty Quantification via Stable Distribution Propagation

Felix Petersen, Aashwin Mishra, Hilde Kuehne +3

We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal appro…