The Gradient: Perspectives on AI cover image

Upol Ehsan on Human-Centered Explainable AI and Social Transparency

The Gradient: Perspectives on AI

00:00

How to Generate Rationales From Using a Neural Machine Translation Approach

This is the phase in my dissertation that I call turn to the machine. We kind of started thinking that, wouldn't it be nice if an AI system talked to you or thought out loud in plain English? So we actually took a sequential decision making environment and made an AI agent navigated while being able to think out loud inplain English. It's really interesting, I think a lot of listeners might now appreciate the importance of this kind of work in terms of the outcome here.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app