Zobrazeno 1 - 9 of 9 pro vyhledávání: '"Zahra Atashgahi"'
1
Unsupervised Online Memory-free Change-point Detection using an Ensemble of LSTM-Autoencoder-based Neural Networks (Extended Abstract)
Autor: Zahra Atashgahi, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy
Publikováno v: 8th ACM Celebration of Women in Computing womENcourage
University of Twente Research Information (Pure Portal)
Change-point detection (CPD) is recognized as being one of the most significant tasks in time series analysis. While offline CPD has been vastly investigated in the last few years, online CPD still suffers from major challenges, such as high dependen
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::5dfd5cf32e994a88033610fdb3e91495
https://research.utwente.nl/en/publications/unsupervised-online-memoryfree-changepoint-detection-using-an-ensemble-of-lstmautoencoderbased-neural-networks-extended-abstract(f6916d3b-b285-4b85-a13f-26741be98feb).html
Zobrazit plný text záznamu
3
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Autor: Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu
Publikováno v: Advances in Neural Information Processing Systems
University of Twente Research Information (Pure Portal)
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The former metho
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::87c6b003312a499feb5e11e0640aff31
https://research.utwente.nl/en/publications/e1fb67c9-1822-4deb-ba82-f50c4b7bc892
Zobrazit plný text záznamu
4
Quick and Robust Feature Selection
Autor: Decebal Constantin Mocanu, Elena Mocanu, Raymond N.J. Veldhuis, Tim van der Lee, Mykola Pechenizkiy, Ghada Sokar, Zahra Atashgahi
Publikováno v: arXiv, 2020:2012.00560. Cornell University Library
Machine Learning, 111(1), 377-414. Springer
Machine Learning, 111. Springer
Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a dataset, has
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f97c58d04ad4d7f98d6d0c7f021d6ea8
https://research.tue.nl/en/publications/8dd30b63-386c-495f-8ce1-fdb226b01a78
Zobrazit plný text záznamu
5
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks
Autor: Zahra Atashgahi, Joost Pieterse, Shiwei Liu, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy
Publikováno v: Machine Learning, 111(12), 4411-4452. Springer
Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a sparse ne
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e3520d36ae009d726b61420bf2976b7
Zobrazit plný text záznamu
6
Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders
Autor: Zahra Atashgahi, Sokar, Ghada A. Z. N., Tim van der Lee, Elena Mocanu, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy
Publikováno v: University of Twente Research Information (Pure Portal)
Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a dataset, has
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::159d6c27fb55fe3d070c2f18129f90c4
https://research.utwente.nl/en/publications/7839ad49-34e3-4c81-994c-f6743286c289
Zobrazit plný text záznamu
9
Robustness of sparse MLPs for supervised feature selection (poster)
Autor: Neil Kichler, Zahra Atashgahi, Decebal Constantin Mocanu
Publikováno v: University of Twente Research Information (Pure Portal)
ISSUE=1;TITLE=Sparsity in Neural Networks: Advancing Understanding and Practice 2021
Deep Neural Networks have seen great success yet require increasingly higher dimensional data to be applied successfully. To reduce the ever-increasing computational, energy and memory requirements, the concept of sparsity has emerged as a leading ap
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0bd66904ffcb32fe265b25d06b33d012
https://research.utwente.nl/en/publications/2515c904-f95d-4a5e-b18a-23c61c230db6
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje