Riskgaming cover image

“Smell can be art, and it also can be science”: AI/ML and digital olfaction

Riskgaming

00:00

How to Build a Graph Neural Network That Predicts the Odor of Molecules

We took molecules and we encoded their graph structure. We fed that as a graph into the algorithm. And then the output was a description, an encoded description of what it smelled like. So we're trying to predict this sparse vector as an output from theGraph neural networks can accept that kind of input. With many thousands of examples of graphs as input and this sparse odor label as an output, we can actually learn the patterns that relates the structure of a molecule to its odor. The model is still in development but has been successfully used for several years now.

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