An introduction to Kolmogorov complexity and its applications (2nd ed.)
An introduction to Kolmogorov complexity and its applications (2nd ed.)
Machine Learning - Special issue on inductive transfer
Learning to learn
Optimality of universal Bayesian sequence prediction for general loss and alphabet
The Journal of Machine Learning Research
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability
Estimating relatedness via data compression
ICML '06 Proceedings of the 23rd international conference on Machine learning
A model of inductive bias learning
Journal of Artificial Intelligence Research
IEEE Transactions on Information Theory
IEEE Transactions on Information Theory
IEEE Transactions on Information Theory
A compression-based dissimilarity measure for multi-task clustering
ISMIS'11 Proceedings of the 19th international conference on Foundations of intelligent systems
Multi model transfer learning with RULES family
MLDM'13 Proceedings of the 9th international conference on Machine Learning and Data Mining in Pattern Recognition
| Hi-index | 0.00 |
In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have been used successfully in practice and PAC analysis of these methods have been developed. But the key notion of relatedness between tasks has not yet been defined clearly, which makes it difficult to understand, let alone answer, questions that naturally arise in the context of transfer, such as, how much information to transfer, whether to transfer information, and how to transfer information across tasks. In this paper we look at transfer learning from the perspective of Algorithmic Information Theory, and formally solve these problems in the same sense Solomonoff Induction solves the problem of inductive inference. We define universal measures of relatedness between tasks, and use these measures to develop universally optimal Bayesian transfer learning methods.