1 citations · 2 across the 8 of their papers we have counts for
8 papers
Directional Curvature from Armijo Backtracking: A Low-Cost Sharpness Probe and a Calibration-Free Learning-Rate Safeguard for Adam
Ashmitha R, Jörg Frochte
Local sharpness, defined by the largest Hessian eigenvalue , sets the maximum stable gradient update size, but its computation would usually require running Lanczos or Hessian…
Physics-Informed Machine Learning Under Small-Data Constraints: Lessons from Abrasive Waterjet Milling
Sarah Grewe, Jörg Frochte
In physically dominated machining processes, experimental datasets are small, expensive, and material-specific; in this regime, data curation, evaluation design, and the form of ph…
When Style Similarity Scores Fail: Diagnosing Raw CSD Cosine in Artist-Style Evaluation
Jörg Frochte
Raw cosine in the 768-dimensional output space of the Contrastive Style Descriptor (CSD) is now widely read as an absolute, calibrated style-fidelity score for text-to-image and st…
Multiple Additive Neural Networks for Structured and Unstructured Data
Janis Mohr, Jörg Frochte
This paper extends and explains the Multiple Additive Neural Networks (MANN) methodology, an enhancement to the traditional Gradient Boosting framework, utilizing nearly shallow ne…
LLMs for Text-Based Exploration and Navigation Under Partial Observability
Stephan Sandfuchs, Maximilian Melchert, Jörg Frochte
Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as…
One-Shot Identification with Different Neural Network Approaches
Janis Mohr, Jörg Frochte
Convolutional neural networks (CNNs) have been widely used in the computer vision community, significantly improving the state-of-the-art. But learning good features often is compu…
Exploring Student Expectations and Confidence in Learning Analytics
Hayk Asatryan, Basile Tousside, Janis Mohr +5
Learning Analytics (LA) is nowadays ubiquitous in many educational systems, providing the ability to collect and analyze student data in order to understand and optimize learning a…
Group and Exclusive Sparse Regularization-based Continual Learning of CNNs
Basile Tousside, Janis Mohr, Jörg Frochte
We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic f…