2012 | OriginalPaper | Buchkapitel
Image Morphing: Transfer Learning between Tasks That Have Multiple Outputs
verfasst von : Daniel L. Silver, Liangliang Tu
Erschienen in: Advances in Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Prior work has reported the benefit of transfer learning on domains of single output tasks for classification or prediction of a scalar. We investigate the use of transfer learning on a domain of tasks where each task has multiple outputs (
ie.
output is a vector). Multiple Task Learning (MTL) and
Context-sensitive
Multiple Task Learning (
cs
MTL) neural networks are considered for a domain of image transformation tasks. Models are developed to transform images of neutral human faces to that of corresponding images of angry, happy and sad faces. The MTL approach proves problematic because the size of the network grows as a multiplicative function of the number of outputs and number of tasks. Empirical results show that
cs
MTL neural networks are capable of developing superior models to single task learning models when beneficial transfer occurs from one or more secondary tasks.