Latest News

Nov 2021: 1 paper (poster) accepted to Pre-register workshop at NeurIPS 2021! See the video here.
Sep 2021: 1 paper (poster) accepted to NeurIPS 2021!
Sep 2021: 1 new talk on Contextual Reinforcement Learning is available online!
Sep 2021: 1 new talk on the Foundations of Data Augmentation is available online!
Sep 2021: I will be speaking at the 5th IPM Advanced School On Computing & Artificial Intelligence (2021) about Learning Context Variables in Contextual Reinforcement Learning!
Sep 2021: I will give a talk on the Foundations of Data Augmentation at the Amirkabir Artificial Intelligence Summer Summit (AAISS) 2021!
Aug 2021: I will be presenting my research on Causal Contextual Reinforcement Learning at the International Interdisciplinary Computational Cognitive Science Summer School!
July 2021: 1 journal paper published!
May 2021: My research proposal has been accepted to Graphcore Academic Programme!
April 2021: 1 paper accepted to SSL-RL ICLR 2021 workshop!
March 2021: I have been selected to join the inaugural cohort of Google Cloud Research Innovators (see the news item)!
March 2021: Our submission to the Network Anomaly Detection Challenge (NAD2021) achieved the 8th place!
March 2021: Received a grant from Google Cloud Credit Research Program for my research project CaRL ($5,000).
Dec 2020: New blog post is out!
Nov 2020: Giving a public lecture at CP Lecture series.
Nov 2020: 1 paper accepted at Pre-register NeurIPS 2020 workshop.
Nov 2020: Received a grant from Google Cloud Credit Research Program for my research project DEVs ($5,000).
Sep 2020: Giving an invited talk at the Cyber-Physical Systems Group, TU Wien.
Sep 2020: Attending the Workshop on Equivariance and Data Augmentation.
Aug 2020: Attending the Theory of Reinforcement Learning Boot Camp.
Aug 2020: I'll be speaking at the Amirkabir Artificial Intelligence Summer Summit (AAISS) 2020.
Jul 2020: Attending the Microsoft Research Frontiers in Machine Learning 2020 virtual event.
Jul 2020: New preprint on arXiv: On Data Augmentation and Adversarial Risk: An Empirical Analysis.
Feb 2020: 1 paper (oral) accepted to "Towards Trustworthy ML:Rethinking Security and Privacy for ML" (ICLR 2020 Workshop).
Nov 2019: Giving an invited talk at the Intelligent Autonomous Systems Group of the Computer Science Department of the Technische Universitaet Darmstadt.
Oct 2019: Awarded the travel grant for the DL/RL summer school in Edmonton, Alberta, Canada by Amii (Alberta Machine Intelligence Institute).
Jun 2019: Successfully defended (Passed with Distinction) my PhD dissertation entitled "Representation Learning and Inference from Signals and Sequences".
July 2019: Attending the CIFAR's DL/RL Summer School in Edmonton, Alberta, Canada.
Jun 2019: Ranked 3rd in the DCASE-2019 Challenge, Task1.B (acoustic scene classification under distribution mismatch).
Jun 2019: 1 paper (poster) accepted to CVPR 2019!
Sep 2018: 1 paper (oral) accepted to NeurIPS 2018, workshop of Interpretability and Robustness in Audio, Speech and Language!
Jun 2018: My research has been featured in Der Standard magazine.

Introduction

I am a Postdoctoral Research Scientist at the Linz Institute of Technology (LIT) AI LAB, and a member of Google Cloud Research Innovators. I received my PhD degree in 2019 on Representation Learning and Inference from Signals and Sequences. In 2014, I joined the Institute of Computational Perecption at the Johannes Kepler University of Linz, where I pursued my PhD.



Research Interests

  • Causal Contextual Reinforcement Learning

    Building agents that can reason, and discover the causal factors of the world.

  • Understanding Deep Learning

    Understanding how deep learning works, and how the underlying building blocks that make DL successful function.

  • Robustness and Generalisation in DL

    Adversarial Machine Learning, Learning under Distribution mismatch, Robustness in DL

  • Representation Learning

    Learning robust representations from genomic data, molecules, audio sequences and images.

  • Generative Modelling

    GANs, VAEs

Selected publications

Here is a list of my selected publications.

Talks



2021


Title of the talk: How Much Is An Augmented Sample Worth?
Description: Teaser at the Pre-register workshop at NeurIPS2021.

Title of the talk: Learning Context Variables in Contextual Reinforcement Learning
Description: Talk at the 5th IPM Advanced School On Computing & Artificial Intelligence (2021).



Title of the talk: Foundations of Data Augmentation
Description: Talk at the Amirkabir Artificial Intelligence Summer Summit (AAISS) 2021.



2020


Title of the talk: Context-Adaptive Reinforcement Learning using Unsupervised Learning of Context Variables
Description: Teaser at the Pre-register workshop at NeurIPS2020.

Title of the talk: CP lecture serries
Description: Public lecture at the CP lecture serries.




Title of the talk: On the Inductive Biases in Data Augmentation and Adversarial Robustness.
Description: Talk at the Amirkabir Artificial Intelligence Summer Summit (AAISS) 2020.



Title of the talk: Adversarial Robustness in Data Augmentation.
Description: Talk at the Towards Trustworthy ML: Rethinking Security and Privacy for ML, ICLR 2020 Workshop.



2019


Title of the talk: Representation Learning under Incomplete and Imprecise Information Conditions.
Description: Talk at the Intelligent Autonomous Systems Group of the Computer Science Department of the Technische Universitaet Darmstadt.



2018


Title of the talk: Deep Within-Class Covariance Analysis for Robust Deep Audio Representation Learning.
Description: Talk at the Interpretability and Robustness in Audio, Speech and Language, NeurIPS 2018 Workshop.

Tweets

Mentoring

If you are from an under represented group, and need help with ML research or similar topics, you can book a mentoring session with me.


Contact

You can reach me on twitter or via email. If you are interested in collaborations or discussions about my research, don't hesitate to contact me!