Umut Onur Yaşar

Umut Onur Yaşar

Applied AI Researcher specializing in Deep Learning and Computer Vision.

About Me

I am an Electrical and Electronics Engineer working at the intersection of Deep Learning and Computer Vision. My research focuses on building efficient, scalable AI systems — from model architecture design to real-world deployment. I am particularly interested in knowledge distillation, object detection, and representation learning.

Beyond engineering, I am drawn to the Renaissance ideal of broad intellectual curiosity. I pursue ongoing study in Mathematics, Physics, Philosophy, and Music — disciplines that I find sharpen both analytical thinking and creative problem-solving.

Research Interests

  • Deep Learning — efficient architectures, knowledge distillation, model compression
  • Computer Vision — object detection, image recognition, visual representation learning
  • Applied AI — bridging research with practical, production-grade systems

Selected Projects

Knowledge Distillation on CIFAR-10 Conducted a systematic study on knowledge distillation with ablation experiments on teacher-student architectures using the CIFAR-10 benchmark. Investigated the effect of temperature scaling, intermediate feature alignment, and loss weighting on student model accuracy and generalization.

Object Detection with RT-DETR on COCO Explored transformer-based real-time object detection using the RT-DETR architecture on the COCO dataset, analyzing trade-offs between detection speed and accuracy in resource-constrained settings.

Background

I hold a degree in Electrical and Electronics Engineering and have developed a strong applied foundation in ML/AI through both academic work (including completion of Stanford’s CS229) and hands-on project experience.

Get in Touch

I am always open to research discussions, collaborations, or just exchanging ideas.