PolymerRNN featured

Greta Harrison

A USC Viterbi research visualization shows a machine learning model, called a recurrent neural network (RNN), that is being used to predict a better polymer structure with high energy storage capacity. A polymer structure is mapped into strings of characters (the white letters) before being fed to the RNN model (the green gear), which will results in a list of candidate polymer structures which likely have better energy storage capacity, indicated by the red tetrahedrons.

Published on August 5th, 2021

Last updated on August 5th, 2021