Wavelet-Based Neural Networks for Explainable AI - Anneke von Seeger

Year
2025
Tags
explainable AI
wavelet neural networks
scattering transform
machine learning
adversarial robustness
mathematical AI
texture analysis
interpretable models
computer vision
feature reduction
trustworthy AI
neural network theory
Minnesota
Summary

Traditional neural networks are powerful but difficult to interpret and vulnerable to small input changes. This research develops wavelet-based neural networks with provable stability guarantees, extending the scattering transform to texture modeling. The approach reduces feature complexity while improving interpretability, enabling more reliable and mathematically explainable AI systems.