Transfer Learning using Kolmogorov Complexity: Basic Theory and Empirical Evaluations

By M. H. Mahmud, Sylvian R. Ray. 2007

65 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Diane Joyce Cook
2. Qiang Yang
3. Mingsheng Long
4. Gabriella Csurka
5. Barbara Caputo
6. Sinno Jialin Pan
7. Narayanan Chatapuram Krishnan
8. Tatiana Tommasi

Citations in the corpus

• Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering (2017, methodology): “On the other hand, from a perspective of Kolmogorov complexity, “transfer should always be use-ful”; any pair of distributions underlying a pair of tasks must have something in common (Mahmud, 2009; Mahmud and Ray, 2008).”
• Transfer Learning for Activity Recognition: A Survey (2013, background): “Mahmud and Ray define a distance metric for measuring the similarity of two tasks based on the conditional Kolmogorov complexity between the tasks and prove some theoretical bounds using this distance measure [39].”
• Learning Categories From Few Examples With Multi Model Knowledge Transfer (2014, methodology): “In [31] the authors used conditional Kolmogorov complexity to measure relatedness between tasks and transfer the right amount of information.”
• A Survey on Transfer Learning (2010, background): “In [68], Mahmud and Ray analyzed the case of transfer learning using Kolmogorov complexity, where some theoretical bounds are proved.”