1 code implementation • NeurIPS 2023 • Ido Ben-Shaul, Ravid Shwartz-Ziv, Tomer Galanti, Shai Dekel, Yann Lecun
Self-supervised learning (SSL) is a powerful tool in machine learning, but understanding the learned representations and their underlying mechanisms remains a challenge.
no code implementations • 10 Feb 2023 • Yuval Zelig, Shai Dekel
We provide proofs of our method for the heat equation on the interval and examples of unique network architectures that are adapted to nonlinear equations on the sphere and the torus.
no code implementations • 11 Jan 2023 • Ido Ben-Shaul, Tomer Galanti, Shai Dekel
Multiplication layers are a key component in various influential neural network modules, including self-attention and hypernetwork layers.
1 code implementation • 18 Apr 2022 • Leon Gugel, Shai Dekel
Phase retrieval is a well known ill-posed inverse problem where one tries to recover images given only the magnitude values of their Fourier transform as input.
no code implementations • 21 Jan 2022 • Ido Ben-Shaul, Shai Dekel
Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches zero.
no code implementations • 14 May 2021 • Ido Ben-Shaul, Shai Dekel
We propose a probe for the analysis of deep learning architectures that is based on machine learning and approximation theoretical principles.
no code implementations • 7 May 2018 • Shai Dekel, Oren Elisha, Ohad Morgan
In this paper we introduce a significant improvement to the popular tree-based Stochastic Gradient Boosting algorithm using a wavelet decomposition of the trees.
no code implementations • 9 Oct 2017 • Oren Elisha, Shai Dekel
In this paper we propose a function space approach to Representation Learning and the analysis of the representation layers in deep learning architectures.
no code implementations • 13 Feb 2016 • Leonid Gugel, Yoel Shkolnisky, Shai Dekel
In this paper we construct a learning architecture for high dimensional time series sampled by sensor arrangements.
no code implementations • CVPR 2013 • Oren Barkan, Jonathan Weill, Amir Averbuch, Shai Dekel
One of the main challenges in Computed Tomography (CT) is how to balance between the amount of radiation the patient is exposed to during scan time and the quality of the CT image.