87
edits
Seminar on Internet Technologies (Winter 2017/2018): Difference between revisions
Seminar on Internet Technologies (Winter 2017/2018) (view source)
Revision as of 11:18, 19 September 2017
, 19 September 2017→Topics
No edit summary |
(→Topics) |
||
| Line 41: | Line 41: | ||
|{{Hl2}} |'''Initial Readings''' | |{{Hl2}} |'''Initial Readings''' | ||
|- | |- | ||
| '''Transfer Learning for Visual Categorization''' | |||
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://ieeexplore.ieee.org/abstract/document/6847217/] | |||
|- | |||
| '''A Survey on Semi-Supervised Learning Techniques''' | |||
Semisupervised learning is a learning standard which deals with the study of how computers and natural systems such as human beings acquire knowledge in the presence of both labeled and unlabeled data. Semisupervised learning based methods are preferred when compared to the supervised and unsupervised learning because of the improved performance shown by the semisupervised approaches in the presence of large volumes of data. Labels are very hard to attain while unlabeled data are surplus, therefore semisupervised learning is a noble indication to shrink human labor and improve accuracy. In this work, this task is to survey some of the key approaches for semi-supervised learning. Note that this topic requires a comparatively high reading effort. | |||
| [http://www.net.informatik.uni-goettingen.de/people/tao_zhao Tao Zhao] | |||
| [https://arxiv.org/abs/1402.4645] | |||
|- | |||
| '''A Survey on Multi-view Learning''' | |||
In recent years, a great many methods of learning from multi-view data by considering the diversity of different views have been proposed. These views may be obtained from multiple sources or different feature subsets. In this work, this task is to survey a number of representative multi-view learning algorithms in different areas and organize and highlight similarities and differences between the variety of multi-view learning approaches. Note that this topic requires a comparatively high reading effort. | |||
| [http://www.net.informatik.uni-goettingen.de/people/tao_zhao Tao Zhao] | |||
| [https://arxiv.org/abs/1304.5634] | |||
|- | |- | ||