Search Results for author: Elnaz Barshan

Found 4 papers, 0 papers with code

RelatIF: Identifying Explanatory Training Examples via Relative Influence

no code implementations25 Mar 2020 Elnaz Barshan, Marc-Etienne Brunet, Gintare Karolina Dziugaite

In this work, we focus on the use of influence functions to identify relevant training examples that one might hope "explain" the predictions of a machine learning model.

Semantics Preserving Adversarial Attacks

no code implementations25 Sep 2019 Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad

While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge.

Semantics Preserving Adversarial Learning

no code implementations10 Mar 2019 Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad

While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge.

Text Classification

Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networks

no code implementations7 Apr 2017 Mohammad Javad Shafiee, Elnaz Barshan, Alexander Wong

In this study, we take a deeper look at the notion of synaptic cluster-driven evolution of deep neural networks which guides the evolution process towards the formation of a highly sparse set of synaptic clusters in offspring networks.

Object Categorization object-detection +1

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