The What-If Tool: Code-Free Probing of Machine Learning Models

The What-If Tool: Code-Free Probing of Machine Learning Models

  • September 16, 2018
Table of Contents

The What-If Tool: Code-Free Probing of Machine Learning Models

How would changes to a datapoint affect my model’s prediction? Does it perform differently for various groups–for example, historically marginalized people? How diverse is the dataset I am testing my model on?

The What-If Tool, showing a set of 250 face pictures and their results from a model that detects smiles. Exploring what-if scenarios on a datapoint. Comparing counterfactuals.

Comparing the performance of two slices of data on a smile detection model, with their classification thresholds set to satisfy the “equal opportunity” constraint. Detecting misclassifications: A multiclass classification model, which predicts plant type from four measurements of a flower from the plant. The tool is helpful in showing the decision boundary of the model and what causes misclassifications.

This model is trained with the UCI iris dataset.

Source: googleblog.com

Tags :
Share :
comments powered by Disqus

Related Posts

Foundations Machine Learning

Foundations Machine Learning

Bloomberg presents ‘Foundations of Machine Learning,’ a training course that was initially delivered internally to the company’s software engineers as part of its ‘Machine Learning EDU’ initiative. This course covers a wide variety of topics in machine learning and statistical modeling. The primary goal of the class is to help participants gain a deep understanding of the concepts, techniques and mathematical frameworks used by experts in machine learning.

Read More
China Is Building a Fleet of Autonomous AI

China Is Building a Fleet of Autonomous AI

A fleet of autonomous, AI-powered submarines is headed into hotly-contested Asian waterways. The vehicles will belong to the Chinese armed forces, and their mission capabilities are likely to raise concerned eyebrows in surrounding countries. If all goes to plan, the first submarines will launch in 2020.

Read More
Carnegie Mellon Researchers Develop New Deepfake Method

Carnegie Mellon Researchers Develop New Deepfake Method

Deepfakes, ultrarealistic fake videos manipulated using machine learning, are getting pretty convincing. And researchers continue to develop new methods to create these types of videos, for better or, more likely, for worse. The most recent method comes from researchers at Carnegie Mellon University, who have figured out a way to automatically transfer the “style” of one person to another.

Read More