InTowards Data SciencebyW Brett KennedyFormulaFeatures: A Tool to Generate Highly Predictive Features for Interpretable ModelsCreate more interpretable models by using concise, highly predictive features, automatically engineered based on arithmetic combinations of…Oct 63
InAI AdvancesbyNikhil AnandMaking LLMs more Truthful with DoLa: The Math Stuff (Part II)If you haven’t read Part I yet, check that out here.Nov 26Nov 26
PyC TeamRelational Concept Bottleneck Models (meet us at NeurIPS 2024)Graph Neural Networks expressivity + concept-based interpretabilityDec 4Dec 4
InTowards Data SciencebyConor O'Sullivan8 Plots for Explaining Linear Regression to a LaymanExplain regression to a non-technical audience with residual, weight, effect and SHAP plotsApr 162Apr 162
InTowards Data SciencebyW Brett KennedyFormulaFeatures: A Tool to Generate Highly Predictive Features for Interpretable ModelsCreate more interpretable models by using concise, highly predictive features, automatically engineered based on arithmetic combinations of…Oct 63
InAI AdvancesbyNikhil AnandMaking LLMs more Truthful with DoLa: The Math Stuff (Part II)If you haven’t read Part I yet, check that out here.Nov 26
PyC TeamRelational Concept Bottleneck Models (meet us at NeurIPS 2024)Graph Neural Networks expressivity + concept-based interpretabilityDec 4
InTowards Data SciencebyConor O'Sullivan8 Plots for Explaining Linear Regression to a LaymanExplain regression to a non-technical audience with residual, weight, effect and SHAP plotsApr 162
PyC TeamInterpretable Concept-Based Memory Reasoning (meet us at NeurIPS 2024)Accurate, interpretable, verifiable deep learning modelsDec 3
PyC TeamThe tale of the deep learning model that failed my driving examConcept-based interpretable deep learning in PyTorch (Chapter 1)Dec 4
InTowards Data SciencebyVadim ArzamasovFind Unusual Segments in Your Data with Subgroup DiscoveryPatient rule induction method finds 35% better segments than previously reportedFeb 22
