Search
Now showing items 1-10 of 112
Variations of Submodularity and Diversity: from Robust Optimization to Markov Chains
(2017-09-25)
The combinatorial concept of submodular set functions has proved to be a very useful discrete structure for optimization in machine learning and its applications. In this talk, I will show recent work on generalizations ...
Multistrategy Learning Methods for Multirobot Systems
(Georgia Institute of Technology, 2003)
This article describes three different methods for introducing machine learning into a hybrid deliberative/reactive architecture for multirobot systems: learning momentum, Q-learning, and CBR wizards. A range of simulation ...
Efficient labeling technique and interpretable deep neural network for the classification of seizures using continuous electroencephalograms
(Georgia Institute of Technology, 2018-04-24)
This thesis focuses on the classification of seizures, together with finding efficient and scalable ways to obtain high-quality datasets in order to train deep neural networks. It was motivated by the need to automate the ...
Teaching robots about human environments: Leveraging human interaction to efficiently learn and use multisensory object affordances
(Georgia Institute of Technology, 2018-01-09)
The real world is complex, unstructured, and contains high levels of uncertainty. Although past work shows that robots can successfully operate in situations where a single skill is needed, they will need a framework that ...
Enabling one-handed input for wearable computing
(Georgia Institute of Technology, 2017-05-30)
A new evolution of computing is emerging around wearable technologies. Wearable computing has been a topic of research for years. However, we are beginning to see adoption by consumers and non-researchers due to advances ...
A computational model for solving raven’s progressive matrices intelligence test
(Georgia Institute of Technology, 2018-05-11)
Graphical models offer techniques for capturing the structure of many problems in real- world domains and provide means for representation, interpretation, and inference. The modeling framework provides tools for discovering ...
Inferring Meal Eating Activities in Real World Settings from Ambient Sounds: A Feasibility Study
(Georgia Institute of Technology, 2015)
Dietary self-monitoring has been shown to be an effective method for weight-loss, but it remains an onerous task despite recent advances in food journaling systems. Semi-automated food journaling can reduce the effort of ...
Novel document representations based on labels and sequential information
(Georgia Institute of Technology, 2015-07-23)
A wide variety of text analysis applications are based on statistical machine learning techniques. The success of those applications is critically affected by how we represent a document. Learning an efficient document ...
The Contextual Bandits Problem: Techniques for Learning to Make High-Reward Decisions
(2017-10-30)
We consider how to learn through experience to make intelligent decisions. In the generic setting, called the contextual bandits problem, the learner must repeatedly decide which action to take in response to an observed ...
The Complexity of Learning Neural Networks
(2017-10-30)
The empirical successes of neural networks currently lack rigorous theoretical explanation. A first step might be to show that data generated by neural networks with a single hidden layer, smooth activation functions and ...