Firat Ozdemir

Firat Ozdemir

Senior Data Scientist

Swiss Data Science Center

I am a Senior Data Scientist at Swiss Data Science Center in Zurich, Switzerland. I work on a range of domain science problems and find the right artificial intelligence tools to solve their respective problems. My long time passion is to develop solutions that will subsequently improve life quality.

Interests
  • Artificial Intelligence
  • Medical Image Analysis
  • Generative Modeling
Education
  • PhD in Computer Vision, 2020

    ETH Zurich, Switzerland

  • MSc in Electrical Engineering and Information Technologies, 2015

    EPFL, Switzerland

  • Exchange semester in Business and Management, 2013

    ISC Paris, France

  • BSc in Electrical and Electronics Engineering, 2013

    Sabanci University, Turkey

Experience

 
 
 
 
 
Swiss Data Science Center
Sr. Data Scientist
October 2019 – Present Zurich, Switzerland

Responsibilities include:

  • Deep learning app development
  • Machine learning research
 
 
 
 
 
ETH Zurich
Scientific assistant
October 2015 – September 2019 Zurich, Switzerland

Responsibilities include:

  • Machine learning research
  • Teaching assistant
  • Collaboration with Balgrist Hospital, Zurich
 
 
 
 
 
ABB Corporate Research
Research Intern
August 2014 – January 2015 Baden-Dättwil, Switzerland
Improving PV Plant Operation via Real Time Cloud Tracking and Solar Forecasting through use of RGB camera, irradiation and temperature sensor and historical PV Plant power production data.
 
 
 
 
 
Inria, Stars Team
Research Intern
June 2013 – September 2013 Sophia Antipolis, France

Development of calibration software tools for scene recognition for the European Commission project Dem@Care. Responsibilities include:

  • Developing an automated 3D contextual scene content transformation tool.
  • Developing a GUI based contextual scene construction tool using RGB-D images from Kinect Camera.

Projects

*
Generative modeling of optoacoustic images
Using our public dataset OADAT to create realistic looking fake optoacoustic images
Generative modeling of optoacoustic images
Active Learning for Segmentation Based on Bayesian Sample Querying
A representativeness metric proposed for the acquisition function of an active learning framework.
Active Learning for Segmentation Based on Bayesian Sample Querying
Supervised Projects
A list of projects I (co-)supervised
Supervised Projects

Publications

(2023). OADAT: Experimental and Synthetic Clinical Optoacoustic Data for Standardized Image Processing. Transactions on Machine Learning Research.

Cite

(2023). Retrospective Uncertainties for Deep Models using Vine Copulas. International Conference on Artificial Intelligence and Statistics.

Cite

(2022). A Bayesian data assimilation framework for lake 3D hydrodynamic models with a physics-preserving particle filtering method using SPUX-MITgcm v1. Geoscientific Model Development.

Cite

(2022). Building a physics-constrained, fast and stable machine learning-based radiation emulator.

Cite

(2022). Learning summary statistics for bayesian inference with autoencoders. SciPost Physics Core.

Cite

Contact