<ul><li>Prototype-based classification learning methods are interpretable but have lower performance compared to deep models.</li><li>Deep Prototype-Based Networks (PBNs) aim to combine interpretability with higher performance.</li><li>The Classification-by-Components (CBC) approach within PBNs has shortcomings in creating contradicting explanations.</li><li>The proposed extension of CBC resolves these issues, improves robustness, and achieves state-of-the-art classification accuracy.</li></ul>

A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations

Discover more