2 papers
cs.LG2025
MLMC: Interactive multi-label multi-classifier evaluation without confusion matrices
Aleksandar Doknic, Torsten Möller
Machine learning-based classifiers are commonly evaluated by metrics like accuracy, but deeper analysis is required to understand their strengths and weaknesses. MLMC is a visual e…
cs.LG2022
FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks
Aleksandar Doknic, Torsten Möller
Despite their effective use in various fields, many aspects of neural networks are poorly understood. One important way to investigate the characteristics of neural networks is to…