Advanced Computing, Mathematics and Data
Newsmakers
May 2018
Chemception Takes a Deeper Look at Chemical Behavior
In a recent conversation with Chemistry World about how deep learning (machine learning algorithms based on layered neural networks) is changing how researchers are exploring chemical behavior, ACMD Division Director Nathan Baker discussed Chemception, a deep convolutional neural network framework developed to predict a molecule’s chemical properties from its structure.
Unlike existing models that perform similar functions and have been built with decades of chemical knowledge, Chemception builds its own models using only two-dimensional pictures of molecules. According to Baker, such capability has potential applications in areas such as biophysics.
Read more in the Chemistry World article: “Machine learning hits the big screen.
