BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Advances in machine learning for molecules - José Miguel Hernánd
 ez-Lobato\, Department of Engineering (University of Cambridge)
DTSTART:20190220T143000Z
DTEND:20190220T153000Z
UID:TALK116122@talks.cam.ac.uk
CONTACT:Alberto J Coca
DESCRIPTION:In this talk\, I will describe two applications of machine lea
 rning to molecule data. First\, I will focus on the problem of efficiently
  searching chemical space for new molecules with optimal properties. I wil
 l describe how to use recent advances in deep generative models to obtain 
 continuous representations of molecules which allow us to automatically ge
 nerate novel chemical structures by performing simple operations in a late
 nt space. These methods can then be connected with Bayesian optimization t
 echniques to accelerate the search for new molecules with optimal properti
 es. In the second part of the talk\, I will focus on the problem of modeli
 ng chemical reactions by predicting electron paths. Chemical reactions can
  be described as the stepwise redistribution of electrons in molecules. As
  such\, reactions are often depicted using “arrow-pushing” diagrams wh
 ich show this movement as a sequence of arrows. I will describe an electro
 n path prediction model to learn these sequences directly from data and sh
 ow that the model recovers a basic knowledge of chemistry without being ex
 plicitly trained to do so.
LOCATION:CMS\, MR14
END:VEVENT
END:VCALENDAR