87
edits
Seminar on Internet Technologies (Winter 2017/2018): Difference between revisions
Seminar on Internet Technologies (Winter 2017/2018) (view source)
Revision as of 10:39, 21 September 2017
, 21 September 2017→Topics
(→Topics) |
(→Topics) |
||
| Line 50: | Line 50: | ||
| [http://www.kdnuggets.com/2015/05/21-essential-data-visualization-tools.html] | | [http://www.kdnuggets.com/2015/05/21-essential-data-visualization-tools.html] | ||
|- | |- | ||
| '''Transfer Learning for Visual Categorization''' | | '''Transfer Learning for Visual Categorization (assigned to Shaheer Asghar)''' | ||
Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In this work, this task is to provide a comprehensive study of state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition. Note that this topic requires a comparatively high reading effort. | Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In this work, this task is to provide a comprehensive study of state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition. Note that this topic requires a comparatively high reading effort. | ||
| [http://www.net.informatik.uni-goettingen.de/people/tao_zhao Tao Zhao] | | [http://www.net.informatik.uni-goettingen.de/people/tao_zhao Tao Zhao] | ||