Jordan Ash will present his masters thesis talk Wednesday, April 22, 2015 at 3:30 in rm 401 His readers are Rob Schapire (adviser) and Barbara Engelhardt. Everyone is invited to attend his talk. His abstract follows below. Title: A Novel Domain Adaptation Solution to the Transductive Transfer Learning Problem Abstract: Most classification algorithms rely on the assumption that training and testing data come from the same distribution. When this assumption is violated, classification performance can be seriously affected. Transfer learning, a new and increasingly popular branch of machine learning, seeks to solve this problem. In this thesis, we introduce a novel transductive transfer learning technique that functions by aligning the training and testing datasets before classification. Our method is motivated by a particular problem involving Magnetoencephalography ( MEG) data classification, but can be used for other transfer learning problems as well.