About Mert

Mert Yuksekgonul is an undergraduate student at Bogazici University, studying Computer Science and Industrial Engineering as a double major. Currrently, he is a Visiting Researcher at MIT - Poggio Lab.

His main goal is building trustworthy deep learning systems. Namely, building algorithms and architectures that are explainable and making interpretable decisions; robust to changes in the environment, distribution shifts and adversarials; and quantifying uncertainty in these decisions.

Before MIT, he was a Research Collaborator at Harvard/Mathis Lab. Previously, he worked as a Research Intern at MPI/Bethge Lab and Mathis Lab in Summer 2019 on out of domain robustness, and as a Research Assistant at Bogazici University working with Dr. Mustafa Gokce Baydogan, working on multiple instance learning.

In the industry, he tackled various problems ranging from Recommendation Systems, Energy Forecasting, Vehicle Routing, Sports Analytics. Past internships include: Data Scientist at Algopoly, Supply Chain Optimization Analyst at Getir, ML Engineer at Armut, Data Analyst at QNB Finansbank.

Interests

  • Deep Learning
  • Interpretability
  • Robustness

Education

  • Double Major: BSc in Computer Engineering and BSc in Industrial Engineering GPA:3.97/4.00, 2016 - Present

    Bogazici University

Recent Publications

Learning Maximally Predictive Prototypes in Multiple Instance Learning

In this work, we propose a simple model that provides permutation invariant maximally predictive prototype generator from a given …

Pretraining boosts out-of-domain robustness for pose estimation

Deep neural networks are highly effective tools for human and animal pose estimation. However, robustness to out-of-domain data remains …

Experience

 
 
 
 
 

Visiting Researcher

Massachusetts Institute of Technology - Poggio Lab

Jul 2020 – Oct 2020 Cambridge, MA, USA
(Remotely) Working on robustness and invariance.
 
 
 
 
 

Research Intern

Bethge Lab & Mathis Lab

Jun 2019 – Sep 2019 Tubingen, Germany
Worked on robustness in pose estimation.
 
 
 
 
 

Research Assistant

Bogazici University

Mar 2019 – Jun 2019 Istanbul
Worked on multiple instance learning and time series classification problems.
 
 
 
 
 

Reserch Assistant

University of Toronto

Sep 2018 – Nov 2018 Toronto
Worked on path planning problems.
 
 
 
 
 

Exchange Student

University of Toronto

Sep 2018 – Jan 2019 Toronto
Exchange term at UofT Computer Science. Completed the semester with 4.0.
 
 
 
 
 

Data Scientist Intern

Algopoly

Aug 2018 – Sep 2018 Istanbul
Worked on time series classification.
 
 
 
 
 

Machine Learning Engineer Intern

Armut

Jun 2018 – Aug 2018 Istanbul
Worked on recommender systems.
 
 
 
 
 

Data Analyst

QNB Finansbank

Jan 2018 – Feb 2018 Istanbul
Worked on customer categorization and ad-hoc analysis in finance.

Accomplish­ments

Bayesian Methods for Machine Learning, High Honors

See certificate

Contact