Atılım Güneş Baydin

Dr Atılım Güneş Baydin
Wolfson Building, Parks Road, Oxford OX1 3QD
Interests
For more up-to-date information, visit my personal page.
My work is at the intersection of generative modeling, probabilistic programming, and deep learning, with an interest in applications of machine learning for scientific discovery. I am currently focusing on enabling efficient probabilistic inference in large-scale simulators, implementing code for distributed training and inference at supercomputing scale in collaboration with Lawrence Berkeley Lab. I am also involved in NASA and ESA Frontier Development Lab programs as faculty and member of the AI Technical Committee.
Biography
I am a Departmental Lecturer in machine learning at the Department of Computer Science and a Senior Researcher in machine learning at the Department of Engineering Science, University of Oxford. A member of Torr Vision Group working with Philip H. S. Torr, I am also a Research Member of the Common Room at Kellogg College, a research consultant for Microsoft Research Cambridge, and a member of European Lab for Learning and Intelligent Systems (ELLIS).
Before my work in Oxford, I was a postdoc with Barak Pearlmutter at the Brain and Computation Lab, National University of Ireland Maynooth. In Ireland I specialized in automatic differentiation (“autodiff”) and its uses in machine learning. I worked on differentiable functional programming, with a special focus on compositionality, higher-order operations, and nesting of forward and reverse differentiation.
I have a PhD in artificial intelligence from Universitat Autònoma de Barcelona, where I was supervised by Ramon Lopez de Mantaras and working with him at the Artificial Intelligence Research Institute (IIIA) of the Spanish National Research Council (CSIC). My research focused on analogical and commonsense reasoning, and I developed a novel graph-based evolutionary algorithm employing semantic networks, influenced by evolutionary epistemology and memetics. I received my bachelor’s degree from Middle East Technical University and a master’s degree from Chalmers University of Technology, where I was working on artificial life and computational physics in the Complex Adaptive Systems programme.
Selected Publications
-
Multi−Channel Auto−Calibration for the Atmospheric Imaging Assembly using Machine Learning
Luiz Fernando Guedes dos Santos‚ Souvik Bose‚ Valentina Salvatelli‚ Brad Neuberg‚ Mark Cheung‚ Miho Janvier‚ Meng Jin‚ Yarin Gal‚ Paul Boerner and Atılım Güneş Baydin
In Astronomy & Astrophysics. Vol. 648. Pages A53. 2021.
Details about Multi−Channel Auto−Calibration for the Atmospheric Imaging Assembly using Machine Learning | BibTeX data for Multi−Channel Auto−Calibration for the Atmospheric Imaging Assembly using Machine Learning | DOI (10.1051/0004-6361/202040051) | Link to Multi−Channel Auto−Calibration for the Atmospheric Imaging Assembly using Machine Learning
-
Toward Machine Learning Optimization of Experimental Design
Atılım Güneş Baydin‚ Kyle Cranmer‚ Pablo de Castro Manzano‚ Christophe Delaere‚ Denis Derkach‚ Julien Donini‚ Tommaso Dorigo‚ Andrea Giammanco‚ Jan Kieseler‚ Lukas Layer‚ Gilles Louppe‚ Fedor Ratnikov‚ Giles C. Strong‚ Mia Tosi‚ Andrey Ustyuzhanin‚ Pietro Vischia and Hevjin Yarar
In Nuclear Physics News. Vol. 31. No. 1. Pages 25–28. 2021.
Details about Toward Machine Learning Optimization of Experimental Design | BibTeX data for Toward Machine Learning Optimization of Experimental Design | DOI (10.1080/10619127.2021.1881364) | Link to Toward Machine Learning Optimization of Experimental Design
-
Towards Global Flood Mapping Onboard Low Cost Satellites with Machine Learning
Gonzalo Mateo−Garcia‚ Joshua Veitch−Michaelis‚ Lewis Smith‚ Silviu Oprea‚ Guy Schumann‚ Yarin Gal‚ Atılım Güneş Baydin and Dietmar Backes
In Scientific Reports. Vol. 11. No. 7249. 2021.
Details about Towards Global Flood Mapping Onboard Low Cost Satellites with Machine Learning | BibTeX data for Towards Global Flood Mapping Onboard Low Cost Satellites with Machine Learning | DOI (10.1038/s41598-021-86650-z) | Link to Towards Global Flood Mapping Onboard Low Cost Satellites with Machine Learning