Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 74Machine Learning
- 70Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 22Natural Language Processing
- 22Reinforcement learning
-
Fall 2010
It is essential for surgeons to have their skill evaluated prior to entering the oper- ating room. Most evaluation methods currently in use are subjective, relying on human judgment to assess trainees. Recently, sensors have been used to track the positions of instruments and the forces applied...
-
Spring 2016
Set expansion aims at expanding a given query seed set into a larger and more complete set by adding elements that are likely to belong to the same grouping as the elements of the query set. This thesis studies the problem of efficient set expansion; in particular, given a collection of data...
-
Fall 2023
The increasing complexity of electric power grids, owing to the integration of Distributed Energy Resources (DER), electric vehicles, energy storage systems, and advanced metering infrastructure, has stimulated a surge in research on machine learning-based state estimation and control. In this...
-
Fall 2015
As wireless devices have emerged as a ubiquitous part of people's everyday lives, the demands for faster wireless communications become even more pressing. Fortunately, the advanced techniques of the physical layer such as multiple-input and multiple-output (MIMO), multi-user detection (MUD),...
-
On Efficient Planning in Large Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
DownloadFall 2023
A practical challenge in reinforcement learning is large action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly optimize a global reward function, which leads to a blow-up in the...
-
Spring 2023
Associative classifiers have shown competitive performance with state-of-the-art methods for predicting class labels. In addition to accuracy performance, associative classifiers produce human readable rules for classification which provides an easier way to understand the decision process of...
-
Fall 2015
We develop a method for searching for Hajós constructions. Our results include the discovery of new constructions for some well-known graphs, including the Grötzsch graph, Chvátal graph, and Brinkmann graph; also, we prove that the first two of these are shortest possible constructions. These are...