Botos Csaba

mail github linkedin google-scholar twitter cv

Botos Csaba; DPhil in Machine Learning at Univesity of Oxford

About me

I have successfully defended my DPhil thesis in Engineering Science at University of Oxford , supervised by Prof. Philip Torr and Dr. Adel Bibi and examined by Prof. Ferenc Huszár and Dr. Oiwi Parker Jones. My research focused on the intersection of machine learning and computer vision, with a special emphasis on domain adaptation, continual learning and self-supervised learning in computationally constrained environments. Before enrolling at the University of Oxford, I obtained my BSc in Bionic Engineering at the Pázmány Péter Catholic University in Budapest, Hungary by winning three thesis awards from the National Council of Student Research Societies.

During my undergraduate studies, I interned at the Institute of Experimental Medicine under the supervision of Dr. Gábor Nyiri, at Verizon Smart Communities under the supervision of Dr. András Horváth. During my DPhil, I have been a research intern at the Intel Embodied AI Lab under the supervision of Matthias Müller.

[DEMO] I am really passionate about communicating ML research to a wide audience and to that end I have found it incredibly helpful to make my own TensorFlow.js visualizations: Domain Partitioning via Adversarial Training, Real-Time Online Continual Learning, Interactive Contrastive Learning. Furthermore, I have been organizing and hosting machine learning seminars with the Cross Disciplinary Machine Learning Research Cluster and the GirlsWhoML outreach program.

Collaboration

I am always open to new collaborations and internships, so feel free to contact me if you have an interesting idea or dataset that you would like to work on together. I am also open to supervising undergraduate and master student projects.

Projects

[DEMO] Generative Adversarial Networks Playground: An interactive visualization toolkit for understanding the training dynamics of GANs.
ganplayground
[DEMO] Label Delay in Continual Learning: How do we utilize data from the future tasks before we have access to their labels?
ldocl-1 ldocl-2
[DEMO] Wolfson Scheduler: An open source project building on a novel vectorized solution for multi-set permutation problems.
[DEMO] Contrastive Learning in your browser!: How can we visualize the metric space learned by contrastive methods such that elementary school students can understand it?
embedding
Diversified Dynamic Routing for Vision Tasks: how can we improve the performance of mixture of experts models by explicitly diversifying the experts?
divdr-project
Multilevel Knowledge Transfer for Cross-Domain Object Detection: How can maximize the transfer of knowledge between different domains using image level, feature level and instance level knowledge transfer?
mkt
Domain Partitioning Network: How can we partition the data distribution efficiently using multiple discriminator networks?
dopanet
Multi-domain classification of cardiac signals with Deep Neural Networks: How to detect cardiac arrhythmia from portable ECG devices?
ecg
SAM: Open-source face recognition framework: Full stack face recognition framework from data collection to model deployment.
sam

Teaching

I have been hosting and organizing Machine Learning Seminars and Reading Groups:

I have been a teaching assistant for the following courses: Furthermore I have organized outreach events for high school students and I have been a mentor for the following summer schools: