Derin Gezgin

I am currently a third-year undergraduate student at Connecticut College, double majoring in Computer Science and Statistics and Data Science.

While pursuing my degrees, I collaborate with professors at Connecticut College, Cornell University, and University of Pennsylvania on research projects in areas such as artificial intelligence for games, computer vision, and software engineering. At the same time, I work as a teaching assistant and grader for multiple Computer Science and Statistics courses. I was also a member of the Connecticut College Computer Science Student Advisory Board as the Diversity Chair.

[Email] [CV] [Scholar] [GitHub] [LinkedIn] [DBLP]

Research

I'm a member of two research labs at Connecticut College: the Autonomous Agent Learning Lab, where I work with Dr. Gary B. Parker and Jim O'Connor, and the Informatics Lab, where I work with Dr. Timothy James Becker. My research in the Autonomous Agent Learning Lab focuses on artificial intelligence for games and evolutionary robotics, while in the Informatics Lab I work on real-world applications of computer vision and machine learning.

Outside of Connecticut College, I collaborate with Dr. Saikat Dutta at Cornell University and Dr. Mayur Naik at the University of Pennsylvania. I contribute to IRIS, a neuro-symbolic framework that combines large language models with static analysis to detect security vulnerabilities across entire software repositories.

Publications

	Evolutionary Optimization of Deep Learning Agents for Sparrow MahjongJim O'Connor, Derin Gezgin, Gary B. Parker AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2025 arXiv Code Cite
	Playing Atari Space Invaders with Sparse Cosine Optimized Policy EvolutionJim O'Connor, Jay B. Nash, Derin Gezgin, Gary B. Parker AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2025 arXiv Code Cite
	A framework for river connectivity classification using temporal image processing and attention based neural networksTimothy James Becker, Derin Gezgin, Jun Yi He Wu, Mary Becker ACM Conference on Computing and Sustainable Societies, 2025 arXiv Code Cite Slides Poster
	SCOPE for Hexapod Gait GenerationJim O'Connor, Jay B. Nash, Derin Gezgin, Gary B. Parker IJCCI Conference on Evolutionary Computation and Theory and Applications, 2025 arXiv Code Cite Poster
	Evolving Neural Controllers for Xpilot-AI Racing Using Neuroevolution of Augmenting TopologiesJim O'Connor, Nicolas Lorentzen, Gary B. Parker, Derin Gezgin IJCCI Conference on Evolutionary Computation and Theory and Applications, 2025 arXiv Code Cite

Teaching Experience

I am lucky to serve as a teaching assistant for the courses below, working with classes of 20–40 students. In the 2025–2026 academic year, I also serve as the COM110 TA Manager, coordinating the TA team and scheduling for night, lab and grading sessions. So far, as an undergraduate student, I have accumulated over 330 hours of TA service.

COM110: Introduction to Computer Science and Problem Solving

Connecticut College • Spring 2024 - Present

Introductory computer science course focused on problem-solving with Python and real-world applications

COM212: Data Structures

Connecticut College • Fall 2024 - Present

Intermediate computer science course in Java focusing on data structures, recursion, and software design

COM219: Computer Organization

Connecticut College • Fall 2025 - Present

Computer organization and architecture, covering hardware, memory, and system levels down to assembly

STA207: Advanced Regression Techniques

Connecticut College • Fall 2025 - Present

Applied regression methods including linear, multiple, and logistic regression with model diagnostics, transformations, and variable selection, using case studies and statistical software to analyze real-world data