Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 2Rabbany khorasgani, Reihaneh
- 2Sacharuk, Edward, 1948-
- 2Sharifi, AmirAli
- 68Machine Learning
- 63Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 21Natural Language Processing
- 20Image processing. Digital techniques.
-
Spring 2018
Skin cancer is one of the common and most fatal cancers. Therefore, it is important to be able to diagnose skin lesions and detect this cancer before it is too late. Learning to distinguish between sick and healthy lesions is key. However, there are two levels in which one can learn to...
-
Fall 2010
Much structured data of scientific interest can be represented as networks, where sets of nodes or vertices are joined together in pairs by links or edges. Although these networks may belong to different research areas, there is one property that many of them do have in common: the network...
-
Spring 2010
Radiotherapy is often used to treat prostate cancer. While using high dose of radiation does kill cancer cells, it can cause toxicity in healthy tissues for some patients. It would be best to apply this treatment only to patients who are likely to be immune from such toxicity. This requires a...
-
Fall 2014
Using motion capture data is an efficient way to generate and transmit 3D character animation. We explore the possibility of incorporating human perceptual factors in compression and synthesis of motion capture data in order to achieve a higher performance in different aspects including reducing...
-
Spring 2015
Graphical models use the intuitive and well-studied methods of graph theory to implicitly represent dependencies between variables in large systems. They can model the global behaviour of a complex system by specifying only local factors.This thesis studies inference in discrete graphical models...
-
Fall 2015
Polarity classification in text is the problem of automatically detecting the general opinion of textual data. Analyzing the general opinion toward a topic of interest is important for different audiences, such as companies, politicians or even regular users. On the other hand, the availability of...
-
Optimal Mechanisms for Machine Learning: A Game-Theoretic Approach to Designing Machine Learning Competitions
DownloadSpring 2013
In this thesis we consider problems where a self-interested entity, called the principal, has private access to some data that she wishes to use to solve a prediction problem by outsourcing the development of the predictor to some other parties. Assuming the principal, who needs the machine...
-
Fall 2011
Scientific literature is constantly being reviewed and critically analyzed by researchers, individually or collaboratively. Collaborative reviewing enables receiving multiple perspectives on the content and extending ideas over each other. Existing collaborative-review tools do not effectively...