Search Results for author: Amnon Geifman

Found 9 papers, 2 papers with code

Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum

no code implementations26 Jul 2023 Amnon Geifman, Daniel Barzilai, Ronen Basri, Meirav Galun

We leverage the duality between wide neural networks and Neural Tangent Kernels and propose a preconditioned gradient descent method, which alters the trajectory of GD.

Inductive Bias

A Kernel Perspective of Skip Connections in Convolutional Networks

no code implementations27 Nov 2022 Daniel Barzilai, Amnon Geifman, Meirav Galun, Ronen Basri

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing.

On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels

no code implementations17 Mar 2022 Amnon Geifman, Meirav Galun, David Jacobs, Ronen Basri

We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels.

Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks

no code implementations7 Apr 2021 Yuval Belfer, Amnon Geifman, Meirav Galun, Ronen Basri

Deep residual network architectures have been shown to achieve superior accuracy over classical feed-forward networks, yet their success is still not fully understood.

Frequency Bias in Neural Networks for Input of Non-Uniform Density

no code implementations ICML 2020 Ronen Basri, Meirav Galun, Amnon Geifman, David Jacobs, Yoni Kasten, Shira Kritchman

Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high frequency ones.

Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings

no code implementations ICCV 2019 Yoni Kasten, Amnon Geifman, Meirav Galun, Ronen Basri

A common approach to essential matrix averaging is to separately solve for camera orientations and subsequently for camera positions.

GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices

1 code implementation CVPR 2019 Yoni Kasten, Amnon Geifman, Meirav Galun, Ronen Basri

First, given ${n \choose 2}$ fundamental matrices computed for $n$ images, we provide a complete algebraic characterization in the form of conditions that are both necessary and sufficient to enabling the recovery of camera matrices.

Cannot find the paper you are looking for? You can Submit a new open access paper.