Content-type: text/html Downes.ca ~ Stephen's Web ~ Learning to Smell: Using Deep Learning to Predict the Olfactory Properties of Molecules

Stephen Downes

Knowledge, Learning, Community

How does our knowledge of smells work? According to this work with machine learning, graphs. "Since molecules are analogous to graphs, with atoms forming the vertices and bonds forming the edges, Graph Neural Networks (GNNs) are the natural model of choice for their understanding.... (a) single vector, representing the entire molecule, can then be passed into a fully connected network as a learned molecular featurization. This network outputs a prediction for odor descriptors, as provided by perfume experts."

Today: 0 Total: 1403 [Direct link] [Share]


Stephen Downes Stephen Downes, Casselman, Canada
stephen@downes.ca

Copyright 2024
Last Updated: Apr 29, 2024 07:25 a.m.

Canadian Flag Creative Commons License.

Force:yes