[Mike Rosenstein]
mtr email

To transfer or not to transfer
M.T. Rosenstein, Z. Marx, L.P. Kaelbling, and T.G. Dietterich. To transfer or not to transfer. To appear, NIPS 2005 Workshop on Inductive Transfer: 10 Years Later, 2005.
Abstract: With transfer learning, one set of tasks is used to bias learning and improve performance on another task. However, transfer learning may actually hinder performance if the tasks are too dissimilar. As described in this paper, one challenge for transfer learning research is to develop approaches that detect and avoid negative transfer using very little data from the target task.
Download: pdf (132KB),
See also:
  Transfer learning with an ensemble of background tasks

updated 09-Dec-2005