Search
Now showing items 1-10 of 28
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 ...
Manipulating state space distributions for sample-efficient imitation-learning
(Georgia Institute of Technology, 2020-03-16)
Imitation learning has emerged as one of the most effective approaches to train agents to act intelligently in unstructured and unknown domains. On its own or in combination with reinforcement learning, it enables agents ...
Establishing a Data Science 101 Pedagogy: Reimagining the MOOC Learning Experience Through a Case-Based Learning Methodology
(Georgia Institute of Technology, 2019-04)
This work involved a comparative analysis of randomly selected Data Science Massive Open Online Courses (MOOCs) and master’s degree programs in investigating how effectively interdisciplinary curricula approaches were being ...
Evaluating visual conversational agents via cooperative human-AI games
(Georgia Institute of Technology, 2019-04-26)
As AI continues to advance, human-AI teams are inevitable. However, progress in AI is routinely measured in isolation, without a human in the loop. It is crucial to benchmark progress in AI, not just in isolation, but ...
Automated iterative game design
(Georgia Institute of Technology, 2016-12-06)
Computational systems to model aspects of iterative game design were proposed, encompassing: game generation, sampling behaviors in a game, analyzing game behaviors for patterns, and iteratively altering a game design. ...
EvalAI: Evaluating AI systems at scale
(Georgia Institute of Technology, 2018-12-06)
Artificial Intelligence research has progressed tremendously in the last few years. There has been the introduction of several new multi-modal datasets and tasks due to which it is becoming much harder to compare new ...
Interpretation, grounding and imagination for machine intelligence
(Georgia Institute of Technology, 2018-11-08)
Understanding how to model computer vision and natural language jointly is a long-standing challenge in artificial intelligence. In this thesis, I study how modeling vision and language using semantic and pragmatic ...
Developing a Document Trained Automated Advisor
(Georgia Institute of Technology, 2018-08)
This paper covers the development of a system to automatically answer questions about the content of a
document. For example, a class syllabus or project specification. The system trains on the document’s content to build ...
Learning to Compose Skills
We present a differentiable framework capable of learning a wide variety of compositions of simple policies that we call skills. By recursively composing skills with themselves, we can create hierarchies that display complex ...
A Theory of Reflective Agent Evolution
(Georgia Institute of Technology, 1998)
Intelligent agents typically operate in complex, dynamic environments. Such environments require that an agent be able to adapt to meet new demands. One promising strategy for such adaptation is to have an agent reason ...