Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Yousefzadeh, Roozbeh"'
Autor:
Yousefzadeh, Roozbeh
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, they still make mistakes, sometimes on cases that appear to be trivial. M
Externí odkaz:
http://arxiv.org/abs/2312.06077
Autor:
Yousefzadeh, Roozbeh, Cao, Xuenan
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 of mathematics as well. Here, we perform a critical inquiry into this
Externí odkaz:
http://arxiv.org/abs/2311.07618
Autor:
Yousefzadeh, Roozbeh, Cao, Xuenan
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: extrapolation, which describes the extent to which AI models can be clueless when
Externí odkaz:
http://arxiv.org/abs/2203.12131
Autor:
Yousefzadeh, Roozbeh
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, consider classification models, e.g., image classification and other
Externí odkaz:
http://arxiv.org/abs/2203.10447
Autor:
Yousefzadeh, Roozbeh
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, generalization of deep networks is considered a mystery. These models have
Externí odkaz:
http://arxiv.org/abs/2203.10366
Autor:
Yousefzadeh, Roozbeh
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 properties of a low-dimensional manifold that models extract and learn from i
Externí odkaz:
http://arxiv.org/abs/2202.04052
Autor:
Yousefzadeh, Roozbeh, Cao, Xuenan
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 complicated mathematical functions that map from an input space to an ou
Externí odkaz:
http://arxiv.org/abs/2201.11260
Autor:
Yousefzadeh, Roozbeh
Medical image datasets can have large number of images representing patients with different health conditions and various disease severity. When dealing with raw unlabeled image datasets, the large number of samples often makes it hard for experts an
Externí odkaz:
http://arxiv.org/abs/2112.12021
Autor:
Yousefzadeh, Roozbeh
The optimal transport problem has many applications in machine learning, physics, biology, economics, etc. Although its goal is very clear and mathematically well-defined, finding its optimal solution can be challenging for large datasets in high-dim
Externí odkaz:
http://arxiv.org/abs/2112.06763
We study the functional task of deep learning image classification models and show that image classification requires extrapolation capabilities. This suggests that new theories have to be developed for the understanding of deep learning as the curre
Externí odkaz:
http://arxiv.org/abs/2112.03411