Zobrazeno 1 - 10
of 121
pro vyhledávání: '"Houle, Michael E."'
Autor:
Huang, Hanxun, Campello, Ricardo J. G. B., Erfani, Sarah Monazam, Ma, Xingjun, Houle, Michael E., Bailey, James
Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality and thus fails to represent the full data distribution and modalities.
Externí odkaz:
http://arxiv.org/abs/2401.10474
Autor:
Anderberg, Alastair, Bailey, James, Campello, Ricardo J. G. B., Houle, Michael E., Marques, Henrique O., Radovanović, Miloš, Zimek, Arthur
We present a nonparametric method for outlier detection that takes full account of local variations in intrinsic dimensionality within the dataset. Using the theory of Local Intrinsic Dimensionality (LID), our 'dimensionality-aware' outlier detection
Externí odkaz:
http://arxiv.org/abs/2401.05453
Intrinsic Dimensionality Estimation within Tight Localities: A Theoretical and Experimental Analysis
Autor:
Amsaleg, Laurent, Chelly, Oussama, Houle, Michael E., Kawarabayashi, Ken-ichi, Radovanović, Miloš, Treeratanajaru, Weeris
Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering. However, since their conve
Externí odkaz:
http://arxiv.org/abs/2209.14475
Publikováno v:
In Information Systems September 2023 118
Subspace Determination through Local Intrinsic Dimensional Decomposition: Theory and Experimentation
Axis-aligned subspace clustering generally entails searching through enormous numbers of subspaces (feature combinations) and evaluation of cluster quality within each subspace. In this paper, we tackle the problem of identifying subsets of features
Externí odkaz:
http://arxiv.org/abs/1907.06771
Generative Adversarial Networks (GANs) are an elegant mechanism for data generation. However, a key challenge when using GANs is how to best measure their ability to generate realistic data. In this paper, we demonstrate that an intrinsic dimensional
Externí odkaz:
http://arxiv.org/abs/1905.00643
Autor:
Ma, Xingjun, Wang, Yisen, Houle, Michael E., Zhou, Shuo, Erfani, Sarah M., Xia, Shu-Tao, Wijewickrema, Sudanthi, Bailey, James
Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs). We propose a new perspective for understanding DNN generalization for such datasets, by investigating the di
Externí odkaz:
http://arxiv.org/abs/1806.02612
Autor:
Ma, Xingjun, Li, Bo, Wang, Yisen, Erfani, Sarah M., Wijewickrema, Sudanthi, Schoenebeck, Grant, Song, Dawn, Houle, Michael E., Bailey, James
Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to make errors during prediction. To better understand such attacks, a characterization is
Externí odkaz:
http://arxiv.org/abs/1801.02613
Autor:
Bailey, James1 (AUTHOR) baileyj@unimelb.edu.au, Houle, Michael E.1 (AUTHOR), Ma, Xingjun2 (AUTHOR)
Publikováno v:
Entropy. Sep2022, Vol. 24 Issue 9, pN.PAG-N.PAG. 32p.
Publikováno v:
In Information Systems July 2016 59:2-14