I am a PhD student at the The Rachel and Selim Benin School of Computer Science and Engineering at the Hebrew University of Jerusalem. My advisor is Prof. Amnon Shashua.
My main research interests are Neural Networks, Graphical Models and Machine Learning in general. I also have a B.Sc. degree in Physics, Mathematics and Computer Science from the Hebrew University. See my complete CV here.
If you are looking for my class notes, you can find them here (website and notes are in Hebrew).
- or.sharir cs.huji.ac.il
- Room B503, Rothberg Buildings, Givat Ram Campus.
- Github-MathJax (Chrome Extension) — a chrome extension for rendering LaTeX equations in Github repositories. Very useful for documenting research projects.
- reprochart — A usefuly python script for easily reproducible charts.
- Generative ConvACs (Experiments) — scripts for reproducing our experiments on Generative ConvACs.
- SimNets (Caffe Fork) — our fork of Caffe with the original implementation of the SimNets architecture.
- Benefits of Depth for Long-Term Memory of Recurrent Networks. arXiv preprint. October, 2017. .
- Sum-Product-Quotient Networks. arXiv preprint. October, 2017. .
- On the Expressive Power of Overlapping Architectures of Deep Learning. arXiv preprint. March, 2017. .
- Tractable Generative Convolutional Arithmetic Circuits. arXiv preprint. October, 2016. (Source Code) .
- On the Expressive Power of Deep Learning: A Tensor Analysis. COLT 2016. June, 2016. .
- Deep SimNets. CVPR 2016. June, 2016. (Source Code) .