I am a Ph.D. candidate in Computer Science at the University at Buffalo, advised by Prof. A. Erdem Sariyüce. My research is in machine learning — image classification, NLP, continual learning, and adversarial ML.
On the teaching side, I have led graduate and undergraduate courses across deep learning and pattern recognition. I work mostly in Python and PyTorch, and I care about bridging research-grade rigor with code that ships.
“We choose to go to the moon in this decade and do the other things, not because they are easy, but because they are hard.” — John F. Kennedy
Teaching
AI Office Hours
A relaxed, no-prerequisites Zoom series on where AI actually is — what LLMs, image models, and agents really do, what they don't, and how to read past the hype. Open a deck full-screen and use the arrow keys to navigate.
-
01
Where AI Actually Is in 2026
A field overview — foundations, the deep-learning revolution, transformers, and generative AI — closing with open Q&A.
Preview inline
Click into the slides, then use the on-screen arrows or your arrow keys. Open full screen ↗
Self-learning resources
Free books I keep pointing students to when they want to dig into machine learning or deep learning on their own.
-
Dive into Deep LearningInteractive textbook with full implementations in PyTorch, MXNet, and JAX. The reference I lean on most in CSE 676.
-
Deep Learning: Foundations and ConceptsA modern volume bridging classical ML to deep learning — the spiritual successor to PRML.
-
Pattern Recognition and Machine LearningThe classic graduate ML text (2006). Rigorous foundation in Bayesian methods, kernels, and graphical models — freely available online as a PDF.