際際滷shows by User: sbaraqouni / http://www.slideshare.net/images/logo.gif 際際滷shows by User: sbaraqouni / Fri, 17 Jun 2016 09:54:42 GMT 際際滷Share feed for 際際滷shows by User: sbaraqouni Certificate /slideshow/certificate-63169206/63169206 10e9aaf3-337d-4269-8b11-769bff3919e2-160617095443
]]>
]]> Fri, 17 Jun 2016 09:54:42 GMT /slideshow/certificate-63169206/63169206 sbaraqouni@slideshare.net(sbaraqouni) Certificate sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/10e9aaf3-337d-4269-8b11-769bff3919e2-160617095443-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Certificate from Shadi Nabil Albarqouni
]]> 160 5 https://cdn.slidesharecdn.com/ss_thumbnails/10e9aaf3-337d-4269-8b11-769bff3919e2-160617095443-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 AggNet: Deep Learning from Crowds /slideshow/aggnet-deep-learning-from-crowds/62538957 aggnet-160530135445
The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7405343]]>
The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7405343]]> Mon, 30 May 2016 13:54:45 GMT /slideshow/aggnet-deep-learning-from-crowds/62538957 sbaraqouni@slideshare.net(sbaraqouni) AggNet: Deep Learning from Crowds sbaraqouni The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7405343 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aggnet-160530135445-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7405343
AggNet: Deep Learning from Crowds from Shadi Nabil Albarqouni
]]> 509 7 https://cdn.slidesharecdn.com/ss_thumbnails/aggnet-160530135445-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Clustering lect /slideshow/clustering-lect/54464746 qltxlotbsxekrczgfirk-signature-9e9dda3850e43c563c53d47d9d96c787ec7fc2d31b5d92aad7556b1e5934efa8-poli-151028072751-lva1-app6891
Clustering lecture is offered for Biomedical Computing Master program in TU Munich. ]]>
Clustering lecture is offered for Biomedical Computing Master program in TU Munich. ]]> Wed, 28 Oct 2015 07:27:51 GMT /slideshow/clustering-lect/54464746 sbaraqouni@slideshare.net(sbaraqouni) Clustering lect sbaraqouni Clustering lecture is offered for Biomedical Computing Master program in TU Munich. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/qltxlotbsxekrczgfirk-signature-9e9dda3850e43c563c53d47d9d96c787ec7fc2d31b5d92aad7556b1e5934efa8-poli-151028072751-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Clustering lecture is offered for Biomedical Computing Master program in TU Munich.
Clustering lect from Shadi Nabil Albarqouni
]]> 472 8 https://cdn.slidesharecdn.com/ss_thumbnails/qltxlotbsxekrczgfirk-signature-9e9dda3850e43c563c53d47d9d96c787ec7fc2d31b5d92aad7556b1e5934efa8-poli-151028072751-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Sparse Regularization /slideshow/sparse-regularization/49510522 mop9pt3zqfyxrlclkabo-signature-4a7e487a5d059ba4cd6baf25de1b99dd5a01489f886f0b84291d18a0ed36790c-poli-150617144501-lva1-app6892
That was my lecture in Machine Learning Practical Course: Introduction to Sparse Methods.]]>
That was my lecture in Machine Learning Practical Course: Introduction to Sparse Methods.]]> Wed, 17 Jun 2015 14:45:01 GMT /slideshow/sparse-regularization/49510522 sbaraqouni@slideshare.net(sbaraqouni) Sparse Regularization sbaraqouni That was my lecture in Machine Learning Practical Course: Introduction to Sparse Methods. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mop9pt3zqfyxrlclkabo-signature-4a7e487a5d059ba4cd6baf25de1b99dd5a01489f886f0b84291d18a0ed36790c-poli-150617144501-lva1-app6892-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> That was my lecture in Machine Learning Practical Course: Introduction to Sparse Methods.
Sparse Regularization from Shadi Nabil Albarqouni
]]> 752 2 https://cdn.slidesharecdn.com/ss_thumbnails/mop9pt3zqfyxrlclkabo-signature-4a7e487a5d059ba4cd6baf25de1b99dd5a01489f886f0b84291d18a0ed36790c-poli-150617144501-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Pmsd https://fr.slideshare.net/slideshow/pmsd/48768261 sdujq3dtd6ysar1wjfqu-signature-601de55dccca0b6300fc998b052d2d08f3fa6777f9228925445283a6a2293c71-poli-150529202106-lva1-app6892
]]>
]]> Fri, 29 May 2015 20:21:06 GMT https://fr.slideshare.net/slideshow/pmsd/48768261 sbaraqouni@slideshare.net(sbaraqouni) Pmsd sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sdujq3dtd6ysar1wjfqu-signature-601de55dccca0b6300fc998b052d2d08f3fa6777f9228925445283a6a2293c71-poli-150529202106-lva1-app6892-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
from Shadi Nabil Albarqouni
]]> 226 2 https://cdn.slidesharecdn.com/ss_thumbnails/sdujq3dtd6ysar1wjfqu-signature-601de55dccca0b6300fc998b052d2d08f3fa6777f9228925445283a6a2293c71-poli-150529202106-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Introduction to Sparse Methods /slideshow/shadi-sparsity/48767877 lwcwf7xqmypqi2cubpv5-signature-49459baad3b4f2df83805f7a4a101ee788648bf968f26a182df1810d50ca8bec-poli-150529201109-lva1-app6891
This is my lecture for Machine Learning for Medical Application (Practical Course) in TUM.]]>
This is my lecture for Machine Learning for Medical Application (Practical Course) in TUM.]]> Fri, 29 May 2015 20:11:09 GMT /slideshow/shadi-sparsity/48767877 sbaraqouni@slideshare.net(sbaraqouni) Introduction to Sparse Methods sbaraqouni This is my lecture for Machine Learning for Medical Application (Practical Course) in TUM. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lwcwf7xqmypqi2cubpv5-signature-49459baad3b4f2df83805f7a4a101ee788648bf968f26a182df1810d50ca8bec-poli-150529201109-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This is my lecture for Machine Learning for Medical Application (Practical Course) in TUM.
Introduction to Sparse Methods from Shadi Nabil Albarqouni
]]> 1332 3 https://cdn.slidesharecdn.com/ss_thumbnails/lwcwf7xqmypqi2cubpv5-signature-49459baad3b4f2df83805f7a4a101ee788648bf968f26a182df1810d50ca8bec-poli-150529201109-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Telemedicine in Palestine /sbaraqouni/telemedicine-in-palestine eykxfkzktjmdl3iuxc9m-signature-39ddfe785472bf9a9ff2d88a47cf58aeefac3ee45ab2239e897dabab154b6fb2-poli-150529200233-lva1-app6892
This is my participation in the 3rd Telemedicine Conference in Palestine organized by GIZ.]]>
This is my participation in the 3rd Telemedicine Conference in Palestine organized by GIZ.]]> Fri, 29 May 2015 20:02:33 GMT /sbaraqouni/telemedicine-in-palestine sbaraqouni@slideshare.net(sbaraqouni) Telemedicine in Palestine sbaraqouni This is my participation in the 3rd Telemedicine Conference in Palestine organized by GIZ. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/eykxfkzktjmdl3iuxc9m-signature-39ddfe785472bf9a9ff2d88a47cf58aeefac3ee45ab2239e897dabab154b6fb2-poli-150529200233-lva1-app6892-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> This is my participation in the 3rd Telemedicine Conference in Palestine organized by GIZ.
Telemedicine in Palestine from Shadi Nabil Albarqouni
]]> 682 2 https://cdn.slidesharecdn.com/ss_thumbnails/eykxfkzktjmdl3iuxc9m-signature-39ddfe785472bf9a9ff2d88a47cf58aeefac3ee45ab2239e897dabab154b6fb2-poli-150529200233-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Pro /slideshow/pro-48767554/48767554 aqqx0krt1mzyl3axajia-signature-4fcd572edf464bb6759e365ecba847c41ab52a5ddd5db392c31e07994a118683-poli-150529195912-lva1-app6891
]]>
]]> Fri, 29 May 2015 19:59:12 GMT /slideshow/pro-48767554/48767554 sbaraqouni@slideshare.net(sbaraqouni) Pro sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/aqqx0krt1mzyl3axajia-signature-4fcd572edf464bb6759e365ecba847c41ab52a5ddd5db392c31e07994a118683-poli-150529195912-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Pro from Shadi Nabil Albarqouni
]]> 187 1 https://cdn.slidesharecdn.com/ss_thumbnails/aqqx0krt1mzyl3axajia-signature-4fcd572edf464bb6759e365ecba847c41ab52a5ddd5db392c31e07994a118683-poli-150529195912-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Medical robots history /slideshow/medical-robots-history-aa/29192240 medicalrobotshistoryaa-131213170631-phpapp01
]]>
]]> Fri, 13 Dec 2013 17:06:31 GMT /slideshow/medical-robots-history-aa/29192240 sbaraqouni@slideshare.net(sbaraqouni) Medical robots history sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/medicalrobotshistoryaa-131213170631-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Medical robots history from Shadi Nabil Albarqouni
]]> 1099 4 https://cdn.slidesharecdn.com/ss_thumbnails/medicalrobotshistoryaa-131213170631-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds document Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Robust Stability and Disturbance Analysis of a Class of Networked Control Systems /slideshow/robust-stability-and-disturbance-analysis-of-a-class-of-networked-control-systems/29192070 final-131213165601-phpapp01
]]>
]]> Fri, 13 Dec 2013 16:56:01 GMT /slideshow/robust-stability-and-disturbance-analysis-of-a-class-of-networked-control-systems/29192070 sbaraqouni@slideshare.net(sbaraqouni) Robust Stability and Disturbance Analysis of a Class of Networked Control Systems sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/final-131213165601-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Robust Stability and Disturbance Analysis of a Class of Networked Control Systems from Shadi Nabil Albarqouni
]]> 652 2 https://cdn.slidesharecdn.com/ss_thumbnails/final-131213165601-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 DIP Course Projects (HCR) /slideshow/dip-course-projects-hcr/29191785 finaldip-1-131213163356-phpapp02
DIP Course is offered as an Elective course for undergraduate students in EE-Islamic University Gaza. The project handles the Handwritten Character Recognition using Neural Networks. ]]>
DIP Course is offered as an Elective course for undergraduate students in EE-Islamic University Gaza. The project handles the Handwritten Character Recognition using Neural Networks. ]]> Fri, 13 Dec 2013 16:33:56 GMT /slideshow/dip-course-projects-hcr/29191785 sbaraqouni@slideshare.net(sbaraqouni) DIP Course Projects (HCR) sbaraqouni DIP Course is offered as an Elective course for undergraduate students in EE-Islamic University Gaza. The project handles the Handwritten Character Recognition using Neural Networks. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/finaldip-1-131213163356-phpapp02-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> DIP Course is offered as an Elective course for undergraduate students in EE-Islamic University Gaza. The project handles the Handwritten Character Recognition using Neural Networks.
DIP Course Projects (HCR) from Shadi Nabil Albarqouni
]]> 1238 7 https://cdn.slidesharecdn.com/ss_thumbnails/finaldip-1-131213163356-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Rigid motions & Homogeneous Transformation /sbaraqouni/rigid-motions-homogeneous-transformation lect04m2-121213174646-phpapp01
]]>
]]> Thu, 13 Dec 2012 17:46:46 GMT /sbaraqouni/rigid-motions-homogeneous-transformation sbaraqouni@slideshare.net(sbaraqouni) Rigid motions & Homogeneous Transformation sbaraqouni <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lect04m2-121213174646-phpapp01-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br>
Rigid motions & Homogeneous Transformation from Shadi Nabil Albarqouni
]]> 1256 4 https://cdn.slidesharecdn.com/ss_thumbnails/lect04m2-121213174646-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-sbaraqouni-48x48.jpg?cb=1563381924 Shadi N. Albarqouni works as a Research Assistant for the Chair of Computer Aided Medical Procedure in Technische Universit辰t M端nchen. He holds a Visiting Scholar position in Center of Advanced European Studies and Research (caesar)/DZNE in Bonn, Germany. His mainly work on developing Image Processing tools for cryo-electron tomographic data. He worked as an Instructor in Faculty of Engineering in The Islamic University of Gaza as well as a Technical Instructor in the University College of Applied Science. He received recently a Scholarship to pursue his PhD in Medical Imaging in the Chair of Computer Aided Medical Procedure & Augmented Reality in Technical University of Munich, Munich,... campar.in.tum.de/Main/ShadiAlbarqouni https://cdn.slidesharecdn.com/ss_thumbnails/10e9aaf3-337d-4269-8b11-769bff3919e2-160617095443-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/certificate-63169206/63169206 Certificate https://cdn.slidesharecdn.com/ss_thumbnails/aggnet-160530135445-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/aggnet-deep-learning-from-crowds/62538957 AggNet: Deep Learning ... https://cdn.slidesharecdn.com/ss_thumbnails/qltxlotbsxekrczgfirk-signature-9e9dda3850e43c563c53d47d9d96c787ec7fc2d31b5d92aad7556b1e5934efa8-poli-151028072751-lva1-app6891-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/clustering-lect/54464746 Clustering lect