Gayane Grigoryan- Doctor of Philosophy
- Machine Learning Postdoctoral Researcher at Georgia Institute of Technology
Gayane Grigoryan
- Doctor of Philosophy
- Machine Learning Postdoctoral Researcher at Georgia Institute of Technology
Analyzing student performance-related data using machine learning, explainable artificial intelligence, and LLMs.
About
11
Publications
2,737
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
55
Citations
Current institution
Publications
Publications (11)
Simulation models, including discrete event simulation, agent-based models, and system dynamics, are employed to study various sce- narios and behaviors. However, understanding these models can be particularly challenging because they depend on varying in- puts and parameters. This study proposes the use of existing and new explainable artificial i...
Higher education programs are rapidly transitioning online in support of a broader geographic base, working professionals, and, recently, emergency contingencies such as COVID-19. The flexibility of online courses makes them attractive to adult learners; as such, there is much academic discussion about online learning for adult learners and the con...
Simulation models are subject to uncertainty and sensitivity, meaning that even small variations of input can cause considerable fluctuations in the output results. Consequently, this can amplify the uncertainty associated with the simulation, thereby limiting the confidence one can have in its outcomes. To mitigate these effects, this paper sugges...
The agent-based simulation (ABS) community has begun a push for inverse generative approaches, that is, using data analytics and machine learning to generate the rules and behaviors in simulations to make them empirically valid. The focus of this community's efforts has been on evolutionary algorithm approaches, particularly genetic programming. Ot...
To date, many reasons have been suggested for making explainable
artificial intelligence (XAI) models. However, it is unclear when the
XAI suggested content is considered an explanation. This paper conducts a survey to determine the requirements for the information
to be considered an explanation. Four minimum requirements have
been prioritized bas...
One of the challenges for agent-based modeling is being able to incorporate human behavior. Human behavior is a multifaceted phenomenon, with strategic coalition formation being one form. A hybrid agent-based modeling approach, called ABMSCORE, has been derived to emulate strategic group formation. In this paper, we describe a simulation experiment...
Game theory is a useful modelling approach to analyse complex
systems with multiple stakeholders, describe their decision-making process, and the impact these decisions have on the overall system performance. In this paper, we review the use of game theory models in the systems engineering domain. Our approach was to conduct an extensive literatur...
Hedonic games have gained interest, by the academic community, in recent years because of their ability to model the grouping preferences of individuals. Hedonic games are an example of non-transferrable utility game in cooperative game theory. Cooperative game theory, or n-person game theory, is a branch of game theory that focuses on coalition fo...
Organizations continually seek to understand the components of cyber risk. A major part of this is understanding how employee behavior influences this risk. In this paper, we examine the connection between an organization’s cyber risk and the level of cyberloafing in its employee population. Cyberloafing, the practice of using company resources for...
