Mehmet Kerem Turkcan

Postdoctoral Research Scientist in Electrical Engineering at Columbia University


7LE3 Schapiro CEPSR

Columbia University

New York, New York 10027

Greetings! I am currently a postdoctoral research scientist in Electrical Engineering at Columbia University specializing in deep learning applications. My research focuses on real-world, low-latency deployment of object detection and trajectory prediction models, and retrieval-augmented generation via large language models. To test algorithms, I lead projects on large-scale data collection and annotation, and improve upon the state-of-the-art models to adapt them to the strict performance requirements of real-world use cases. Right now, my focus is specifically on applications to urban streetscapes and robotic surgeries.

Previously, as a member of the Bionet group, I studied the efficient initialization and execution of very-large-scale, real connectome and synaptome driven, single-synapse-level simulations of neural circuits on GPUs for the purpose of understanding realistic neural networks. Using the tools I developed, I worked on the design of computational circuits for understanding the mushroom body and the lateral horn, two brain regions in insects linked with associative and evolutionary memories. I am also one of the main developers of an open-source interactive neuroscientific computing platform called FlyBrainLab (FBL) that enables access to, manipulation of and simulations for fruit fly brain data.


Jun 5, 2024 Our paper, “Data-Driven Traffic Simulation for an Intersection in a Metropolis”, has been accepted into the POETS Workshop at CVPR 2024!
May 7, 2024 Our paper, “Evaluating Zero-Shot Image Tagging for Urban Traffic Intersection Scenes”, has been accepted into the VAND Workshop at CVPR 2024!
May 1, 2024 I will be a Co-Chair of the CS3 Student Leadership Council of the Center for Smart Streetscapes for the 2024-2025 cycle!
Apr 29, 2024 I received the Electrical Engineering Distinguished Teaching Award for my teaching achievements in 2023!
Oct 25, 2023 I will be in Boston to present our work on transfer learning for low-resource surgical phase segmentation at the ACS Clinical Congress 2023.

Selected Publications

  1. The Fruit Fly Brain Observatory: From Structure to Function
    Nikul H Ukani, Chung-Heng Yeh, Adam Tomkins, and 8 more authors
    BioRxiv, 2019
  2. Accelerating with FlyBrainLab the discovery of the functional logic of the Drosophila brain in the connectomic and synaptomic era
    Aurel A Lazar, Tingkai Liu, Mehmet Kerem Turkcan, and 1 more author
    Elife, 2021
  3. A Programmable Ontology Encompassing the Functional Logic of the Drosophila Brain
    Aurel A Lazar, Mehmet Kerem Turkcan, and Yiyin Zhou
    Frontiers in Neuroinformatics, 2022
  4. Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
    Chengbo Zang, Mehmet Kerem Turkcan, Sanjeev Narasimhan, and 8 more authors
    Bioengineering, 2023
  5. Optimizing Computer Vision in Surgery Workflows Through Transfer Learning
    Mehmet Kerem Turkcan, Sarah Choksi, Daniel P. Bitner, and 4 more authors
    In American College of Surgeons Clinical Congress 2023, Oct 2023