Krzysztof J. Geras

Assistant Professor
Department of Radiology
New York University School of Medicine

(also affiliated at)
Center for Data Science
New York University


Address: Office 313, 660 1st Avenue, New York, NY 10016.

About me

I recently started as an assistant professor at the NYU School of Medicine. I previously worked as a postdoctoral researcher at the NYU Center for Data Science with Prof. Kyunghyun Cho, Prof. Linda Moy and Prof. Sungheon G. Kim.

My main interests are unsupervised learning with neural networks, model compression, transfer learning and evaluation of machine learning models.

During my PhD studies at the University of Edinburgh I was supervised by Dr. Charles Sutton. My PhD was kindly sponsored by SICSA and EPSRC. Prior to studying towards a PhD in Machine Learning, I got my BSc and MSc degrees in Computer Science from the University of Warsaw. I worked on my MSc thesis as a visiting student at the University of Edinburgh under the supervision of Dr. Amos Storkey, my second supervisor was Prof. Andrzej Szałas. My thesis was on Machine Learning Markets. I also did industrial internships in Microsoft Research (Redmond, working with Rich Caruana and Abdel-rahman Mohamed), Amazon (Berlin, Ralf Herbrich's group), Microsoft (Bellevue) and J.P. Morgan (London).


Google Scholar profile

Classifier-agnostic saliency map extraction
Konrad Żołna, Krzysztof J. Geras and Kyunghyun Cho
[pdf | bib | code]

Breast density classification with deep convolutional neural networks
Nan Wu, Krzysztof J. Geras, Yiqiu Shen, Jingyi Su, S. Gene Kim, Eric Kim, Stacey Wolfson, Linda Moy and Kyunghyun Cho
ICASSP, 2018
[pdf | bib | code]

High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks
Krzysztof J. Geras, Stacey Wolfson, Yiqiu Shen, Nan Wu, S. Gene Kim, Eric Kim, Laura Heacock, Ujas Parikh, Linda Moy and Kyunghyun Cho
[pdf | bib | code]

Exploiting diversity for efficient machine learning
Krzysztof J. Geras
PhD thesis, University of Edinburgh, 2017.
[pdf | bib]

Do Deep Convolutional Nets Really Need to be Deep (Or Even Convolutional)?
Gregor Urban, Krzysztof J. Geras, Samira Ebrahimi Kahou, Ozlem Aslan, Shengjie Wang, Rich Caruana, Abdel-rahman Mohamed, Matthai Philipose and Matthew Richardson
ICLR, 2017.
[pdf | bib]

Composite denoising autoencoders
Krzysztof J. Geras and Charles Sutton
ECML PKDD, 2016.
[pdf | bib]

Analysis of Deep Neural Networks with Extended Data Jacobian Matrix
Shengjie Wang, Abdel-rahman Mohamed, Rich Caruana, Jeff Bilmes, Matthai Plilipose, Matthew Richardson, Krzysztof Geras, Gregor Urban and Ozlem Aslan
ICML, 2016.
[pdf | bib]

Blending LSTMs into CNNs
Krzysztof J. Geras, Abdel-rahman Mohamed, Rich Caruana, Gregor Urban, Shengjie Wang, Ozlem Aslan, Matthai Philipose, Matthew Richardson and Charles Sutton
ICLR (workshop track), 2016.
[pdf | bib]

Scheduled denosing autoencoders
Krzysztof J. Geras and Charles Sutton
ICLR, 2015.
[pdf | bib]

Multiple-source cross-validation
Krzysztof J. Geras and Charles Sutton
ICML, 2013.
[pdf | bib]

Isoelastic agents and wealth updates in machine learning markets
Amos Storkey, Jono Millin and Krzysztof J. Geras
ICML, 2012.
[pdf | bib]

Prediction Markets for Machine Learning
Krzysztof J. Geras
MSc thesis, University of Warsaw, 2011.
[pdf | bib]