activity
20192022
most citedInterpreting Neural Networks Using Flip Points

6 citations · 21 across the 11 of their papers we have counts for

collaborators

15 papers

cs.LG2022

Should Machine Learning Models Report to Us When They Are Clueless?

Roozbeh Yousefzadeh, Xuenan Cao

The right to AI explainability has consolidated as a consensus in the research community and policy-making. However, a key component of explainability has been missing: extrapolati…

cs.LG20221 cited

Over-parameterization: A Necessary Condition for Models that Extrapolate

Roozbeh Yousefzadeh

In this work, we study over-parameterization as a necessary condition for having the ability for the models to extrapolate outside the convex hull of training set. We specifically,…

cs.LG20222 cited

Deep Learning Generalization, Extrapolation, and Over-parameterization

Roozbeh Yousefzadeh

We study the generalization of over-parameterized deep networks (for image classification) in relation to the convex hull of their training sets. Despite their great success, gener…

cs.CV2022

Decision boundaries and convex hulls in the feature space that deep learning functions learn from images

Roozbeh Yousefzadeh

The success of deep neural networks in image classification and learning can be partly attributed to the features they extract from images. It is often speculated about the propert…

cs.LG20224 cited

To what extent should we trust AI models when they extrapolate?

Roozbeh Yousefzadeh, Xuenan Cao

Many applications affecting human lives rely on models that have come to be known under the umbrella of machine learning and artificial intelligence. These AI models are usually co…

cs.LG2021

Federated Learning without Revealing the Decision Boundaries

Roozbeh Yousefzadeh

We consider the recent privacy preserving methods that train the models not on original images, but on mixed images that look like noise and hard to trace back to the original imag…