Combining Symbolic and Neural Learning
Machine Learning
Extraction of rules from discrete-time recurrent neural networks
Neural Networks
Machine Learning - Special issue on inductive transfer
A perspective view and survey of meta-learning
Artificial Intelligence Review
Neural Computation
The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
CloseGraph: mining closed frequent graph patterns
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty
Artificial Intelligence Review
Co-clustering based classification for out-of-domain documents
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Iterative Reinforcement Cross-Domain Text Classification
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
On universal transfer learning
Theoretical Computer Science
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Symbol grounding through cumulative learning
EELC'06 Proceedings of the Third international conference on Emergence and Evolution of Linguistic Communication: symbol Grounding and Beyond
| Hi-index | 0.02 |
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.