https://www.aidancooper.co.uk/a-non-technical-guide-to-interpreting-shap-analyses/ Explaining Machine Learning Models: A Non-Technical Guide to Interpreting SHAP AnalysesAidan CooperNov 1, 2021With interpretability becoming an increasingly important requirement for machine learning projects, there’s a growing need for
What I Read: CNN Heat Maps, Class Activation Mapping
https://glassboxmedicine.com/2019/06/11/cnn-heat-maps-class-activation-mapping-cam/ CNN Heat Maps: Class Activation Mapping (CAM)Date: June 11, 2019Author: Rachel Draelos “Class Activation Mapping (CAM) is one technique for producing heat maps to highlight class-specific regions of images.”
What I Read: Be Careful Interpreting Predictive Models, Causal Insights
https://towardsdatascience.com/be-careful-when-interpreting-predictive-models-in-search-of-causal-insights-e68626e664b6 Be Careful When Interpreting Predictive Models in Search of Causal InsightsA careful exploration of the pitfalls of trying to extract causal insights from modern predictive machine learning models.Scott Lundberg
What I Read: Branch Specialization
https://distill.pub/2020/circuits/branch-specialization/ Branch SpecializationChelsea VossGabriel GohNick CammarataMichael PetrovLudwig SchubertChris OlahApril 5, 2021DOI 10.23915/distill.00024.008 “Branch specialization occurs when neural network layers are split up into branches. The neurons and circuits tend to
What I Read: Visualizing Weights
https://distill.pub/2020/circuits/visualizing-weights/ Visualizing WeightsChelsea VossNick CammarataGabriel GohMichael PetrovLudwig SchubertBen EganSwee Kiat LimChris OlahFeb. 4, 2021DOI 10.23915/distill.00024.007 “The problem of understanding a neural network is a little bit like reverse engineering a