2 papers
cs.AI2026
Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA)
Markus Klute, Artur Monsch, Lars Sowa +1
We introduce a rigid and comprehensive taxonomy and paradigm for characterizing the influence of the input feature space on the predictions of a neural network (NN) u…
hep-ph2026
An Optimal Observable Machine for reinterpretable measurements in high-energy physics
Torben Mohr, Alejandro Quiroga Triviño, Fabian Riemer +6
A machine-learning-based framework for constructing generator-level observables optimized for parameter extraction in particle physics analyses is introduced, referred to as the Op…