Knowledge Transfer using Multiresolution Learning
by Eric Eaton
Wednesday, March 7, 2007, 15:30pm - Wednesday, March 7, 2007, 17:00pm
The use of multiple resolutions allows the selective transfer of knowledge at specific levels of generalization between tasks. The proposed work focuses on two mechanisms for performing multiresolution transfer. The first method, data-based multiresolution transfer, uses multiple resolutions of input data to create models at different resolutions. The second method, model-based multiresolution transfer, generates multiple resolutions of previously learned models and then selectively transfers the appropriate resolution of the model. An additional contribution of this work will be a general framework for knowledge transfer that provides a foundation for comparing different transfer methods.