Assistant Professor, PhD,
Dept. of Mathematics and Computer Science, Széchenyi István University, Győr, Hungary,
E-mail: , Phone: +36/96503400/3261, Office: B610.
I received MSc in informatics (2004), and PhD in machine learning (2010) from the Budapest University of Technology and Economics.
My main research interests are machine learning and artificial intelligence.
I am part time consultant at Gravity R&D.
I like competitions.
My program Tyson won the 2nd Hungarian Computer Go-moku Open Tournament (2005).
I was the captain of The Ensemble team that finished second in the Netflix Prize competition (2009).
I won third prize in the GE Flight Quest (2013).
I am organizing an annual programming contest for the students of my university.
- G. Takács, D. Tikk, Alternating least squares for personalized ranking, received Honorable Mention at 6th ACM Conference on Recommender Systems (RecSys 2012), Dublin, Ireland, 2012. [pdf] [erratum]
- G. Takács, Convex polyhedron learning and its applications, PhD thesis, Budapest University of Technology and Economics, Faculty of Electrical Engineering and Informatics, Budapest, Hungary, 2010. [pdf]
- G. Takács, I. Pilászy, B. Németh, D. Tikk, Scalable collaborative filtering approaches for large recommender systems, Journal of Machine Learning Research (Special Topic on Mining and Learning with Graphs and Relations), 10: 623-656, 2009. [pdf]
- G. Takács, I. Pilászy, B. Németh, D. Tikk, Investigation of various matrix factorization methods for large recommender systems, Proc. of the 2nd KDD Workshop on Large Scale Recommender Systems and the Netflix Prize Competition, Las Vegas, Nevada, USA, 2008. [pdf]
- Parmod: Framework for massively parallel simulations on unstructured meshes (2010-2011).
- Gravity@Netflix: Movie recommender system (2006-2009).
- Tyson: Tournament winner go-moku AI (2003-2007).
- TgMammo: Computer-aided breast cancer detection in X-ray images (2003-2005).
- TgLetter: An experimental postal code recognition system (2003).
- Recognizer: Handwritten digit recognition with neural networks (2002).