Dan Rosenbaum

  

Dan Rosenbaum

School of Computer Science and Engineering
The Hebrew University of Jerusalem
email: danrsm at cs dot huji dot ac dot il

cv

I am now a research scientist at DeepMind.
I completed my PhD at the Hebrew University of Jerusalem, under the supervision of Prof. Yair Weiss.
My main research interests are machine learning and computer vision.
I'm currently working on learning generative models and approximate inference in vision problems.

Publications

Learning Models for Visual 3D Localization With Implicit Mapping
Dan Rosenbaum, Frederic Besse, Fabio Viola, Danilo J. Rezende, S. M. Ali Eslami.   [pdf]
Neural Processes
Marta Garnelo, Jonathan Schwarz, Dan Rosenbaum, Fabio Viola, Danilo J. Rezende, S.M. Ali Eslami, Yee Whye Teh.   [arXiv]
Conditional Neural Processes
Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami. ICML 2018.  [arXiv]
Neural Scene Representation and Rendering
S. M. A. Eslami, D. Jimenez Rezende, F. Besse, F. Viola, A. S. Morcos, M. Garnelo, A. Ruder-man, A. A. Rusu, I. Danihelka, K. Gregor, D. P. Reichert, L. Buesing, T. Weber, O. Vinyals, D. Rosenbaum, N. Rabinowitz, H. King, C. Hillier, M. Botvinick, D. Wierstra, K. Kavukcuoglu, and D. Hassabis. Science 2018.  [pdf, Science]
Learning Generative Models and the Inference Process in Low Level Vision
Dan Rosenbaum. PhD thesis.  [pdf]
Statistics of RGBD images
Dan Rosenbaum and Yair Weiss.   [arXiv]
Subspace Learning with Partial Information
Alon Gonen, Dan Rosenbaum, Yonina Eldar, Shai Shalev-Shwartz. JMLR 2016.  [pdf]
The Return of the Gating Network: Combining Generative Models and Discriminative Training in Natural Image Priors
Dan Rosenbaum and Yair Weiss. NIPS 2015.  [pdf, supp, code]
Beyond Brightness Constancy: Learning Noise Models for Optical Flow
Dan Rosenbaum and Yair Weiss.   [arXiv]
Learning the Local Statistics of Optical Flow
Dan Rosenbaum, Daniel Zoran and Yair Weiss. NIPS 2013.  [pdf]
Pedestrian Collision Warning System
Dan Rosenbaum, Amiad Gurman, Yonatan Samet, Gideon P. Stein and David Aloni. Mobileye 2012 US patent US20120314071.
Forward Collision Warning Trap and Pedestrian Advanced Warning System
Dan Rosenbaum, Amiad Gurman and Gideon P. Stein. Mobileye 2012 US patent US20120140076.
Information Processing for Optimal Behavior
MSc. thesis supervised by Naftali Tishby 2010.   [pdf]

Teaching

TA in Introduction to Digital Signal Processing 2011-2014