PinnedConor O'Sullivan·Jan 31, 2025Grad-CAM for Explaining Computer Vision ModelsUnderstanding the math, intuition and Python code for Gradient-weighted Class Activation Mapping (Grad-CAM)
PinnedInTDS ArchivebyConor O'Sullivan·Dec 19, 2021Introduction to SHAP with PythonHow to create and interpret SHAP plots: waterfall, force, mean SHAP, beeswarm and dependenceA response icon12A response icon12
PinnedInTDS ArchivebyConor O'Sullivan·Feb 12, 20247 Lessons from an ML Internship at IntelAutomation, machine learning and LLMs in the chip industryA response icon8A response icon8
PinnedInTDS ArchivebyConor O'Sullivan·Sep 19, 2022What is Explainable AI (XAI)?An introduction to XAI— the field aimed at making machine learning models understandable to humansA response icon1A response icon1
PinnedInTDS ArchivebyConor O'Sullivan·Apr 29, 2022Analysing Fairness in Machine LearningDoing an exploratory fairness analysis and measuring fairness using equal opportunity, equalized odds and disparate impactA response icon1A response icon1
InTDS ArchivebyConor O'Sullivan·Oct 16, 2024The Accuracy vs Interpretability Trade-off Is a LieWhy, if we look at the bigger picture, black-box models are not more accurateA response icon4A response icon4
InTDS ArchivebyConor O'Sullivan·Oct 8, 2024Evaluating Edge Detection? Don’t Use RMSE, PSNR or SSIMEmpirical and theoretical evidence for why Figure of Merit (FOM) is the best edge-detection evaluation metricA response icon1A response icon1
InTDS ArchivebyConor O'Sullivan·Sep 30, 2024Explaining Anomalies with Isolation Forest and SHAPIsolation Forest is an unsupervised, tree-based anomaly detection method. See how both KernelSHAP and TreeSHAP can be used to explain its…A response icon6A response icon6
InTDS ArchivebyConor O'Sullivan·Sep 10, 2024Do We Really Need Deep Learning for Coastal Monitoring?An in-depth exploration of how machine learning stacks up against traditional coastal erosion monitoring methodsA response icon3A response icon3
InTDS ArchivebyConor O'Sullivan·Jun 26, 2024A Deep Dive on LIME for Local InterpretationsThe intuition, theory, and code for Local Interpretable Model-agnostic Explanations (LIME)
