Tag: Model Interpretability

Data Ethics: Contesting Truth and Rearranging Power

This Domino Data Science Field Note covers Chris Wiggins's recent data ethics seminar at Berkeley. The article focuses on 1) proposed frameworks for defining and designing...

Themes and Conferences per Pacoid, Episode 9

Paco Nathan's latest article features several emerging threads adjacent to model interpretability. Introduction Welcome back to our monthly burst of themes and conferences. Several technology conferences...

Addressing Irreproducibility in the Wild

This Domino Data Science Field Note provides highlights and excerpted slides from Chloe Mawer’s "The Ingredients of a Reproducible Machine Learning Model" talk at a recent...

Model Interpretability with TCAV (Testing with Concept Activation Vectors)

This Domino Data Science Field Note provides very distilled insights and excerpts from Been Kim’s recent MLConf 2018 talk and research about Testing with Concept Activation Vectors...

Justified Algorithmic Forgiveness?

Last week, Paco Nathan referenced Julia Angwin’s recent Strata keynote that covered algorithmic bias. This Domino Data Science Field Note dives a bit deeper into some...

Trust in LIME: Yes, No, Maybe So? 

In this Domino Data Science Field Note, we briefly discuss an algorithm and framework for generating explanations, LIME (Local Interpretable Model-Agnostic Explanations), that may help data...

Make Machine Learning Interpretability More Rigorous

This Domino Data Science Field Note covers a proposed definition of machine learning interpretability, why interpretability matters, and the arguments for considering a rigorous evaluation of...

On Ingesting Kate Crawford’s “The Trouble with Bias”

Kate Crawford discussed bias at a recent SF-based City Arts and Lectures talk and a recording of the discussion will be broadcast, May 6th, on KQED and...