Academy House, CB2 8PA
I have joined AstraZeneca in Cambridge as an AI Researcher in the Respiratory and Immunology machine learning group.
Prior to that, I was a Research Associate on the SpeechWave project at the Department of Engineering, King’s College London. The project involved a collaboration with the Center for Speech Technology Research, University of Edinburgh. The main focus of the project was on developing learning algorithms for noise robust speech recognition in the waveform domain. Prior to joining King’s College London, I worked as a Research Assistant at the University of Nottingham whilst being a doctoral candidate at the University of Bonn. Namely, I started my doctorate at the Department of Informatics in Bonn and moved to the UK shortly after my advisor accepted a professorship in Nottingham.
I am interested in theoretical aspects of machine learning and techniques for the design and analysis of computationally efficient learning algorithms. In addition to this, I am interested in artificial intelligence and its applications such as speech recognition and the design of materials and molecules. I also maintain an active interest in numerical and functional analysis, causality, randomized algorithms, non-convex optimization, graph theory, and signal processing. My primary research interests include:
I am also closely following the developments in the following machine learning research areas:
- Reliable and robust machine learning
- Causal generative models and causal inference
- Active optimization
- Bayesian deep learning
- Federated learning
- Self-supervised learning
|Oct 16, 2021||
New technical report @ arXiv
Towards Robust Waveform-Based Acoustic Models
|Aug 16, 2021||
Paper published @ IEEE/ACM Transactions on Audio, Speech, and Language Processing, doi: 10.1109/TASLP.2021.3104193
Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks
|Aug 6, 2021||
Paper accepted @ IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
D. Oglic, Z. Cvetkovic, and P. Sollich – Learning Waveform-Based Acoustic Models using Deep Variational Convolutional Neural Networks
(pdf to be released soon)
|Jul 23, 2021||
Best Reviewer Award @ ICML 2021
A certificate in recognition of the contribution as a Top 10% Reviewer for the 38th International Conference on Machine Learning.
|Jun 4, 2021||
Paper published @ Journal of Machine Learning Research (JMLR)
Towards a Unified Analysis of Random Fourier Features
|Mar 2, 2021||
Paper accepted @ Journal of Machine Learning Research (JMLR)
Z. Li, J-F. Ton, D. Oglic, and D. Sejdinovic – Towards a Unified Analysis of Random Fourier Features (pdf to be released soon)
This is an extension of the paper that received an Honorable Mention – Best Paper Award at ICML 2019.
|Oct 30, 2020||
Starting with AstraZeneca in Cambridge (November 2020)
Delighted to announce that I will be joining AstraZeneca in Cambridge as an AI Researcher in Respiratory and Immunology.
I would like to use this opportunity to thank my advisors, collaborators, and three institutions (University of Bonn, University of Nottingham, and King’s College London) for the support in the past eight years.
|Oct 12, 2020||
Released code for the paper to be presented at INTERSPEECH 2020
Automatic Speech Recognition with MXNet and Kaldi