[Research] Lab meeting: Wednesday March 24

[Artur Dubrawski]

Time: The First Wednesday of Spring, 12:00noon

Place: NSH 1507 (Karen W. to confirm that)

Speaker: David Anqi Cui

Title: Active Learning Algorithms for Fast Drug Discovery

Abstract:

In this talk, I will show my work during the past six months. The
project is based on drug discovery which usually costs a lot of time
and money. Chemists have to do many experiments to screen useful
compounds. In this paper, we present active learning algorithms for
fast drug discovery. The algorithms decrease the number of experiments
required to find out the best performance compounds among plenty of
possible trials. The problem is a traditional exploration vs.
exploitation dilemma and our approach is based on the multi-armed
bandit problem and other function approximators. We propose the
expected improvement estimation as a method to measure the unknown
compounds. Some traditional models including UCB algorithms, Gaussian
process, regression trees and so on are also used for this problem.
Our results show that the algorithms present in this paper
significantly raise the best performance of compounds found within a
certain number of picks. The number of picks needed to first discover
the best compound are also reduced to about half of random method's
cost.

See you all there!