Interpretable Machine Learning Comparison Hub

3 papers - avg viability 6.7

Reference Surfaces

TT-Sparse: Learning Sparse Rule Models with Differentiable Truth Tables(8.0)
TT-Sparse offers a novel approach to interpretable machine learning by learning sparse rule models with differentiable truth tables, providing high predictive performance and low complexity, making it suitable for high-stakes decision-making.
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse(7.0)
Adaptive Manifold Prototypes (AMP) improves classification accuracy and interpretability by representing class prototypes as orthonormal bases on the Stiefel manifold, preventing prototype collapse.
Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data(5.0)
Develop Behavior Learning framework to enable interpretable hierarchical optimization in machine learning models integrated with behavioral science.