Mutual information (MI) is fundamental to representation-learning analysis in deep networks, but in high dimensions MI estimators depend on hyperparameters whose bias often dominates the signal. We show that continuous piecewise-linear (CPWL) networks, including ReLU networks, admit an intrinsic information-theoretic a...
Johan Mylius-Kroken, Elisabeth Wetzer, Ali Ramezani-Kebrya et al.· 0 citations
Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural fidelity, rely on prespecified corpora, or explain models post-hoc. We propose Polytopal Neural Networks (PNNs), a framework that extracts distinct layer-wise aspects by...
A. E. J. Wedenborg, A. V. Nørskov, Teresa Dorszewski et al.· 0 citations
Recent machine learning weather prediction (MLWP) models have demonstrated remarkable forecasting skill on global reanalysis-based benchmarks. However, their performance remains unclear in challenging environments such as Northern Norway, where narrow fjords and rapidly changing weather result in highly variable local...
Si-Yan Chen, Lars Uebbing, E. Samuelsen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
