10 citations · 12 across the 3 of their papers we have counts for
3 papers
cs.LG2024
Pixel-Based Similarities as an Alternative to Neural Data for Improving Convolutional Neural Network Adversarial Robustness
Elie Attias, Cengiz Pehlevan, Dina Obeid
Convolutional Neural Networks (CNNs) excel in many visual tasks but remain susceptible to adversarial attacks-imperceptible perturbations that degrade performance. Prior research r…
cs.NE2019★ 2 cited
Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks
Dina Obeid, Hugo Ramambason, Cengiz Pehlevan
Synaptic plasticity is widely accepted to be the mechanism behind learning in the brain's neural networks. A central question is how synapses, with access to only local information…
cond-mat.stat-mech2009★ 10 cited
State selection in the noisy stabilized Kuramoto-Sivashinsky equation
D. Obeid, J. M. Kosterlitz, B. Sandstede
In this work, we study the 1D stabilized Kuramoto Sivashinsky equation with additive uncorrelated stochastic noise. The Eckhaus stable band of the deterministic equation collapses…