Sun.Jan 20, 2019

article thumbnail

Model Interpretability with TCAV (Testing with Concept Activation Vectors)

Domino Data Lab

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 (TCAV), an interpretability method that allows researchers to understand and quantitatively measure the high-level concepts their neural network models are using for prediction, “ even if the concept was not part of the training “ If interested in additional insights not provided in this blog post, please refe

Testing 63
article thumbnail

New Year. New Goals. New Era of Analytics. Are you ready?

DataRobot Blog

by Jen Underwood. A long time has passed since I’ve last written. Thank you to my peers that have reached out and asked what’s going on. Rapidly growing DataRobot keeps me extremely busy. Read More.

article thumbnail

Usage-Driven Groupings of Data Science and Machine Learning Programming Languages

Business Over Broadway

Analysis of usage patterns of 16 data science programming languages by over 18,000 data professionals showed that programming languages can be grouped into a smaller set (specifically, 5 groupings). That is, some programming languages tend to be used together apart from other programming languages. A few of the different groupings of languages reflect specific types of applications or specific roles that data professionals could support, including analytics, general-purpose, and front-end effort