Finding Trust and Transparency in Artificial Intelligence

TL;DR: It’s possible but there’s no magic wand.

Dandelion seeds floating away in a sunset. Photo by Dawid Zawiła on Unsplash

The Importance of Industry Standards

Todd Moore presenting at Open Source Summit EU 2019 on Trusted AI and the LF AI Trusted AI Committee

Fairness and Bias Mitigation

Kush Varshney presents about AIF360 at Reinforce Conference in March 2019. Kush also co-directs the IBM Science for Social Good initiative.

Improving Explainability

Decision Tree to guide you in choosing the right algorithms for explaining the outcomes of your models. Find more on the AIX360 website.

Preventing Adversarial Attacks

Adversarial Robustness 360 Toolbox demo app showing a C&W Attack on a picture of a siamese cat showing that the image detection output thinks it is now an ambulance! Check it out here: https://art-demo.mybluemix.net/

Building Transparency

We show you a few fun ways to take advantage of MAX. There are models to help answer questions, recognize yoga poses, or even to make music with the flick of a wrist. Learn about these and more on IBM Developer.

Continual Learning…

--

--

Things we made with data at IBM’s Center for Open Source Data and AI Technologies.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Maureen McElaney

OSS DevRel at @IBM . board @vtTechAlliance . my words don’t represent my employer. (http://pronoun.is/she/:or/they)