Sciweavers

AAAI
2006

Cross-Domain Knowledge Transfer Using Structured Representations

13 years 5 months ago
Cross-Domain Knowledge Transfer Using Structured Representations
Previous work in knowledge transfer in machine learning has been restricted to tasks in a single domain. However, evidence from psychology and neuroscience suggests that humans are capable of transferring knowledge across domains. We present here a novel learning method, based on neuroevolution, for transferring knowledge across domains. We use many-layered, sparsely-connected neural networks in order to learn a structural representation of tasks. Then we mine frequent sub-graphs in order to discover sub-networks that are useful for multiple tasks. These sub-networks are then used as primitives for speeding up the learning of subsequent related tasks, which may be in different domains.
Samarth Swarup, Sylvian R. Ray
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2006
Where AAAI
Authors Samarth Swarup, Sylvian R. Ray
Comments (0)