interpretability – Page 3 – Andrew Fairless, Ph.D.

What I Read: Bayesian Media Mix Modeling

By Andrew Fairless on October 7, 2021September 21, 2021

Bayesian Media Mix Modeling for Marketing OptimizationBenjamin Vincent2021-09-17 “Fortunately, with Bayesian modeling, we can do better than this! So-called Media Mix Modelling (MMM) can estimate how effective each advertising channelContinue readingWhat I Read: Bayesian Media Mix Modeling

What I Read: AI Story Generation

By Andrew Fairless on September 22, 2021September 4, 2021

https://thegradient.pub/an-introduction-to-ai-story-generation/ An Introduction to AI Story Generation21.Aug.2021Mark Riedl “To tell a story, an intelligent system has to have a lot of knowledge, both about how to tell a story andContinue readingWhat I Read: AI Story Generation

What I Read: XGBoost, Order Does Matter

By Andrew Fairless on September 13, 2021August 20, 2021

https://towardsdatascience.com/xgboost-order-does-matter-60d8d0d5aa71?gi=d051128bfa6b XGBoost: Order Does MatterWhat impact does the order of the features have on XGBoost models, and how can you use feature importance to identify related features in your data?BityaContinue readingWhat I Read: XGBoost, Order Does Matter

What I Read: CNN Heat Maps, Class Activation Mapping

By Andrew Fairless on July 30, 2021July 12, 2021

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: Human-Centered Explainable AI

By Andrew Fairless on June 24, 2021June 7, 2021

https://thegradient.pub/human-centered-explainable-ai/ Towards Human-Centered Explainable AI: the journey so farby Upol EhsanMay 10 2021 3:41 AM “Not only did this system have commendable accuracy, it also tried to explain its decisionContinue readingWhat I Read: Human-Centered Explainable AI

What I Read: Be Careful Interpreting Predictive Models, Causal Insights

By Andrew Fairless on June 9, 2021May 30, 2021

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 LundbergContinue readingWhat I Read: Be Careful Interpreting Predictive Models, Causal Insights

What I Read: Weight Banding

By Andrew Fairless on May 5, 2021April 10, 2021

https://distill.pub/2020/circuits/weight-banding/ Weight BandingMichael PetrovChelsea VossLudwig SchubertNick CammarataGabriel GohChris OlahApril 8, 2021DOI 10.23915/distill.00024.009 “Open up any ImageNet conv net and look at the weights in the last layer. You’ll find aContinue readingWhat I Read: Weight Banding

What I Read: Branch Specialization

By Andrew Fairless on May 4, 2021April 10, 2021

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 toContinue readingWhat I Read: Branch Specialization

What I Read: Visualizing Weights

By Andrew Fairless on May 3, 2021April 10, 2021

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 aContinue readingWhat I Read: Visualizing Weights

Tag: interpretability