7 citations · 34 across the 22 of their papers we have counts for
14 papers · 1 filter
A Lean Dataset for International Math Olympiad: Small Steps towards Writing Math Proofs for Hard Problems
Roozbeh Yousefzadeh, Xuenan Cao, Azim Ospanov
Using AI to write formal proofs for mathematical problems is a challenging task that has seen some advancements in recent years. Automated systems such as Lean can verify the corre…
An Ambiguity Measure for Recognizing the Unknowns in Deep Learning
Roozbeh Yousefzadeh
We study the understanding of deep neural networks from the scope in which they are trained on. While the accuracy of these models is usually impressive on the aggregate level, the…
Large Language Models' Understanding of Math: Source Criticism and Extrapolation
Roozbeh Yousefzadeh, Xuenan Cao
It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding…
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…
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,…
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…
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…
Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Models
Roozbeh Yousefzadeh, Jessica A. Mollick
We study the functional task of deep learning image classification models and show that image classification requires extrapolation capabilities. This suggests that new theories ha…
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…
Deep Learning Generalization and the Convex Hull of Training Sets
Roozbeh Yousefzadeh
We study the generalization of deep learning models in relation to the convex hull of their training sets. A trained image classifier basically partitions its domain via decision b…
Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
Roozbeh Yousefzadeh, Dianne P. O'Leary
Deep learning models have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Nevertheless, they are consist…
Investigating Decision Boundaries of Trained Neural Networks
Roozbeh Yousefzadeh, Dianne P O'Leary
Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial…
Refining the Structure of Neural Networks Using Matrix Conditioning
Roozbeh Yousefzadeh, Dianne P O'Leary
Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of th…
Interpreting Neural Networks Using Flip Points
Roozbeh Yousefzadeh, Dianne P. O'Leary
Neural networks have been criticized for their lack of easy interpretation, which undermines confidence in their use for important applications. Here, we introduce a novel techniqu…