During their thesis defense, PhD candidates introduce and motivate the problems they attacked during their course of studies, defend the novelty and significance of their research, and contextualize their contributions within their field. This is the final step in the process of obtaining a PhD, and a successful defense indicates the acknowledgment of the doctoral #committee that the candidate is an expert in their field. The defense talks are open to all members of the RPI community, and we welcome those interested to attend.
Computer Science Poster Session
Come out and see the research that our MS in Computer Science students are conducting! The MS Poster Session has combined with the RCOS poster session!
Scalable Cost-Efficient Techniques for Machine Learning via Sketching
Dong Hu Advisor: Prof. Alex Gittens
The ever-increasing size and complexity of modern datasets have created a significant challenge for machine learning theorists and experimentalists, as the computational resources and time required to process and analyze these datasets are immense.
An Ontology-Enabled Approach for User-Centered and Knowledge-Enabled Explanations of AI Systems
Shruthi Chari
from Committee: Prof. Deborah L. McGuinness (Chair), Prof. Oshani Seneviratne (Co-Chair), Prof. James A. Hendler, Dr. Prithwish Chakraborty, Dr. Pablo Meyer
The evolution of explainability approaches in Artificial Intelligence (AI) is a significant journey, mirroring the advancements in AI methods from expert systems to modern deep learning.
Computer Science MS Poster Session
MS Graduate Students
Student: Matthew UrygaAdvisor: Prof. Oshani SeneviratnePoster Title: DeFi Data Analysis
Student: Matthew CirimeleAdvisor: Prof. Konstatin KuzminPoster Title: One-Word Natural Language Classification
Student: Daniel SavidgeAdvisor: Prof.
Bergeron: Combating Adversarial Attacks by Emulating a Conscience
Matthew Pisano
from Advisor: Mei Si
Artificial Intelligence alignment is the practice of encouraging an AI to behave in a manner that is compatible with human values and expectations.
Incorporating Context into Knowledge Graph Completion Methods
Sola Shirai
from Advisor: Deborah McGuinness
Knowledge Graph Completion (KGC) methods serve as a valuable tool to identify missing information in a knowledge graph (KG), such as predicting a missing relation between two entities or inferring properties about an entity which does not currently e
