About Me

I am a PhD student at Chalmer University of Technology, advised by Fredrik Johansson and Devdatt Dubhashi. I have received Hon. BS from the University of Toronto in Nov 2018, where I majored in physics and minored in mathematics and statistics. I obtained my master's in statistics at Yildiz Technical University in Aug 2022. I have extensive machine learning experince from NLP and outlier detection to neural graphics.

Currently, I am in the Healthy AI Lab in Chalmers. My research is focused on non-linear independent component analysis, and causal representation learning. You can see my teaching materials and research here.

shape

Publications

Preprints


  • On a notion of outliers based on ratios of order statistics, joint with Oğuz Gürerk; preprint available on arxiv.
  • Order Statistics Based Training and Scoring Algorithms for Deep Outlier Detection; presented in ICAS 2022 conference, available upon request.
  • Adaptive Slot-filling for Turkish Natural Language Understanding; IEEE Xplore, 7th International Conference on Computer Science and Engineering (UBMK), 2022.

    • In Prepearation


  • Extensions of the stochastic SEIR model with vaccination and heterogeneous mixing, an optimal control approach, joint with Oğuz Gürerk. Current version 6 pp.
  • Conditional Random Fields based on Sentence Representations. Current version 5 pp.

    • Teaching & Talks

    Teaching

    Student Assistant; Yildiz Technical University, Department of Statistics:

  • IST 3121 - Regression Analysis I, Fall 2019
  • IST 5110 - Advanced Regression Analysis, Spring 2020

    • Selected Talks

  • Martingales and Black-Scholes Equation, Probability and Statistics Seminars, Boğaziçi University, Istanbul — June 2020
  • Dimension Reduction Techniques for Multivariate Data, Graduate Student Seminars, Yildiz Technical University, Istanbul — Nov 2020
  • Deep Learning Solutions of Differential Equations, Graduate Student Seminars, Yildiz Technical University, Istanbul — Feb 2020
  • Concentration of Measure and Almost Spherical Sections, Student Seminars in Analysis, Boğaziçi University, Istanbul — Jan 2021
  • Outliers and Anomalies, Probability and Statistics Seminars, Boğaziçi University, Istanbul — Jan 2021

    • Research

    Outliers, order statistics, and concentration inequalities

  • Main goal of our project is to have a distribution invariant robust estimator for anomalies based on order statistics.
  • Studying the distribution and the asymptotic behaviour of the chosen statistic.
  • Developing a python library for heavy-tailed data, anomalous data generation and order statistic simulations.

    • Optimal Control in Epidemiological Systems

  • Developing a variant of the SIR models that accounts for vaccination, waning immunity in order to do formulate an optimal control problem for best vaccination policies.
  • Responsible for simulations of the SIR model and for computationally solution of the optimal control problem.

    • Distilling transformer models for a low data setting

  • Main goal of the project is to establish a fast training model for an interactive dialogue system.
  • We developed a model which used transfer learning based on pre-trained transformers and used a hyper-parameter optimization like training on Conditional Random Fields.
  • Using word-piece tokenization to help differentiate between word roots and suffixes agglutinative languages such as Turkish.

    • Research for an embedding guided RNN

  • Main goal of the project is to effectively incorporate predetermined memory state based into a recurrent neural network, which can selectively memorise past states in the sequence.
  • We expected that with the selection of a good memory state we may in affect reduce the need for training time and data.

    • Teaching Materials and Personal