Filters








17 Hits in 1.2 sec

Uncertainty-Aware Deep Classifiers using Generative Models [article]

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
2020 arXiv   pre-print
Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data
more » ... is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.
arXiv:2006.04183v1 fatcat:bjtwcwpxf5bw3bni2d4tpvpn6m

Probiotics and Treatment of Vulvovaginal Candidiasis

Somayeh Saleki, Malihe Farid, Leila Azizi, Mehrnoosh Amiri, Maryam Afrakhteh
2017 International Journal of Enteric Pathogens  
doi:10.15171/ijep.2018.06 fatcat:zaklpwkwibhz5iuhfycevxuvae

Misclassification Risk and Uncertainty Quantification in Deep Classifiers

Murat Sensoy, Maryam Saleki, Simon Julier, Reyhan Aydogan, John Reid
2021 2021 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this paper, we propose risk-calibrated evidential deep classifiers to reduce the costs associated with classification errors. We use two main approaches. The first is to develop methods to quantify the uncertainty of a classifier's predictions and reduce the likelihood of acting on erroneous predictions. The second is a novel way to train the classifier such that erroneous classifications are biased towards less risky categories. We combine these two approaches in a principled way. While
more » ... g this, we extend evidential deep learning with pignistic probabilities, which are used to quantify uncertainty of classification predictions and model rational decision making under uncertainty. We evaluate the performance of our approach on several image classification tasks. We demonstrate that our approach allows to (i) incorporate misclassification cost while training deep classifiers, (ii) accurately quantify the uncertainty of classification predictions, and (iii) simultaneously learn how to make classification decisions to minimize expected cost of classification errors.
doi:10.1109/wacv48630.2021.00253 fatcat:uzi2qsdlsjhi5k6jyreet5vi64

Determination of Fatty Acids Profile and Physicochemical Study of Sea Lettuce (Ulva lactuca) Oil from Bushehr City Coasts

Soror Shaghuli, Ammar Maryamabadi, Gholam Hossean Mohebbi, Alireza Barmak, Saead Armin, Amir Vazirizadeh, Samira Gudarzi, Maryam Saleki
2017 Iranian South Medical Journal  
‫جنوب‬ ّ ‫طب‬ ‫دوماهنامه‬ ‫زيست‬ ‫پژوهشكده‬ -‫فارس‬ ‫خليج‬ ‫پزشكي‬ ‫بوشهر‬ ‫درماني‬ ‫بهداشتي‬ ‫خدمات‬ ‫و‬ ‫پزشكي‬ ‫علوم‬ ‫دانشگاه‬ ‫شماره‬ ‫بيستم،‬ ‫سال‬ 2 ‫صفحه‬ ، 262 -241 ‫تير‬ ‫و‬ ‫(خرداد‬ 2136 ) * ‫بوشهر،‬ ‫خلیج‬ ‫دریایی‬ ‫فناوری‬ ‫زیست‬ ‫تحقیقات‬ ‫مرکز‬ ‫بوشهر‬ ‫بوشهر،‬ ‫پزشکی‬ ‫علوم‬ ‫دانشگاه‬ ‫پزشکی،‬ ‫زیست‬ ‫علوم‬ ‫پژوهشکده‬ ‫فارس،‬ ، ‫ایران‬ mohebbihsn@yahoo.com : E-mail ‫تعیین‬ ‫پروفایل‬ ‫اسیدهای‬ ‫چرب‬ ‫و‬ ‫بررسی‬ ‫فیزیکوشیمیایی‬ ‫ر‬ ‫وغن‬ ‫کاهوی‬ ‫دریایی‬ ( Ulva lactuca ) ‫سواحل‬
more » ... هر‬ ‫بوشهر‬ ‫شاغولي‬ ‫سرور‬ 2 ‫و‬ 2 ، ‫مريم‬ ‫عمار‬ ‫آبادی‬ 1 ، ‫محبي‬ ‫غالمحسين‬ 2 * ، ‫برمک‬ ‫عليرضا‬ 4 ‫آرمين‬ ‫سعيده‬ ، 1 ، ‫وزيری‬ ‫امير‬ ‫زاده‬ 5 ، ‫گودرزی‬ ‫سميرا‬ 2 ، ‫سالك‬ ‫مريم‬ ‫ي‬ 2 2 ‫بوشهر‬ ‫خرد‬ ‫عالي‬ ‫آموزش‬ ‫موسسه‬ -‫ايران‬ 2 ‫خليج‬ ‫دريايي‬ ‫فناوری‬ ‫زيست‬ ‫تحقيقات‬ ‫مرکز‬ ‫بوشهر‬ ‫بوشهر،‬ ‫پزشكي‬ ‫علوم‬ ‫دانشگاه‬ ‫پزشكي،‬ ‫زيست‬ ‫علوم‬ ‫پژوهشكده‬ ‫فارس،‬ ، ‫ايران‬ 1 ‫بوشهر‬ ‫ليان،‬ ‫زيتون‬ ‫شاخه‬ ‫فني‬ ‫بازرسي‬ ‫شرکت‬ ‫توسعه،‬ ‫و‬ ‫تحقيق‬ ‫واحد‬ ، ‫ايران‬ 4 ‫دارو،‬ ‫و‬ ‫غذا‬ ‫معاونت‬ ‫بوشهر‬ ‫بوشهر،‬ ‫پزشكي‬ ‫علوم‬ ‫دانشگاه‬ ، ‫ايران‬ 5
doi:10.29252/ismj.20.2.143 fatcat:dn5hprxgmnfzpbatnnbkxvbdpe

Uncertainty-Aware Deep Classifiers Using Generative Models

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data
more » ... is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.
doi:10.1609/aaai.v34i04.6015 fatcat:v5lveat4e5fxte3w4pvymkpmzi

Acute direct effects of cyclosporine on extracellular field potential of isolated rabbit AV node during experimental atrial fibrillation

Vahid Khori, Sepideh Shariatnezhad, Ali Alizadeh, Hamidreza Yazdi, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Hamidreza Moheimani, Saeed Saleki, Mohsen Nayebpour
2012 Physiology and Pharmacology   unpublished
Previous studies have indicated a relationship between MPTP pore and AV nodal rate-dependent
fatcat:msn5axpby5aztabstwrl3uohyu

Acute direct effects of cyclosporine on extracellular field potential of isolated rabbit AV node during experimental atrial fibrillation

Vahid Khori, Sepideh Shariatnezhad, Ali Alizadeh, Hamidreza Yazdi, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Hamidreza Moheimani, Saeed Saleki, Mohsen Nayebpour
2012 Physiology and Pharmacology   unpublished
Previous studies have indicated a relationship between MPTP pore and AV nodal rate-dependent
fatcat:jiuqz2cc45edtcgzsjxx7uiesa

Acute direct effects of cyclosporine on extracellular field potential of isolated rabbit AV node during experimental atrial fibrillation

Vahid Khori, Sepideh Shariatnezhad, Ali Alizadeh, Hamidreza Yazdi, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Hamidreza Moheimani, Saeed Saleki, Mohsen Nayebpour
2012 Physiology and Pharmacology   unpublished
Previous studies have indicated a relationship between MPTP pore and AV nodal rate-dependent
fatcat:yc2kctrdr5btjgrasfw4w25ley

Frequency-dependent electrophysiological properties of concealed slow pathway of isolated rabbit atrioventricular node preparation after fast pathway ablation in a functional model

Vahid Khori, Samaneh Naeimipour, Ali Alizadeh, Ali Rouhani, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Sepideh Shariatnezhad, Hamidreza Moheimani, Saeed Saleki, Mohammad Zeyghami, Mohsen Nayebpour
Physiology and Pharmacology   unpublished
Intranodal pathways of atrioventricular (AV) node play a vital role in the delay of conduction time in
fatcat:aq7xeuy2vzai3pjkqlijl4jilm

Frequency-dependent electrophysiological properties of concealed slow pathway of isolated rabbit atrioventricular node preparation after fast pathway ablation in a functional model

Vahid Khori, Samaneh Naeimipour, Ali Alizadeh, Ali Rouhani, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Sepideh Shariatnezhad, Hamidreza Moheimani, Saeed Saleki, Mohammad Zeyghami, Mohsen Nayebpour
Physiology and Pharmacology   unpublished
Intranodal pathways of atrioventricular (AV) node play a vital role in the delay of conduction time in
fatcat:veydxhva75fpxau6unqxolpcbm

Role of nitric oxide on the electrophysiological properties of isolated rabbit atrioventricular node by extracellular field potential during atrial fibrillation

Vahid Khori, Ali-Mohammad Alizadeh, Ameneh Navaeian, Mohsen Nayebpour, Mona Pourabouk, Fakhri Badaghabadi, Shima Changizi, Maryam Rajaei, Hamidreza Moheimani, Hamidreza Yazdi, Saeed Saleki
2011 Physiology and Pharmacology   unpublished
The aim of the present study was to determine direct effects of NO modulation on protective
fatcat:yr34wnd7ybcptbnfwnpc63tzpa

Frequency-dependent electrophysiological properties of concealed slow pathway of isolated rabbit atrioventricular node preparation after fast pathway ablation in a functional model

Vahid Khori, Samaneh Naeimipour, Ali Alizadeh, Ali Rouhani, Mona Pourabouk, Fakhri Badaghabadi, Maryam Rajaei, Sepideh Shariatnezhad, Hamidreza Moheimani, Saeed Saleki, Mohammad Zeyghami, Mohsen Nayebpour
Physiology and Pharmacology   unpublished
Intranodal pathways of atrioventricular (AV) node play a vital role in the delay of conduction time in
fatcat:djqysrhq3jgafguf7yg2ejnzzy

Role of nitric oxide on the electrophysiological properties of isolated rabbit atrioventricular node by extracellular field potential during atrial fibrillation

Vahid Khori, Ali-Mohammad Alizadeh, Ameneh Navaeian, Mohsen Nayebpour, Mona Pourabouk, Fakhri Badaghabadi, Shima Changizi, Maryam Rajaei, Hamidreza Moheimani, Hamidreza Yazdi, Saeed Saleki
2011 Physiology and Pharmacology   unpublished
The aim of the present study was to determine direct effects of NO modulation on protective
fatcat:tt7rhefuevdv7eoayvv3433ppy

Factors Hindering towards Purchase of organic Food Products

Uma.R , Dr.V.Selvam
2016 IOSR Journal of Humanities and Social Science  
and Seyedh Maryam Seyedsaleki (2012) proved that organic culture, environmental concern, price, subjective norms, quality and familiarity affect attitudes and thereby purchasing organic food.  ...  the consumer's attitudetowards buying organic food.Overall satisfaction of consumers for organic food is more than inorganic food but the satisfaction level varies due to different factors.Zenab sayed saleki  ... 
doi:10.9790/0837-2107089296 fatcat:2zymoqb3xfawzoy6w2e3v2hbni

Analysis of Awareness among Consumers towards Organic Food Products: With Reference to Vellore Organic Consumers Perspective

Uma, V Selvam
2016 International Journal of Engineering Technology, Management and Applied Sciences www.ijetmas.com   unpublished
Zenab sayed saleki and Seyedh Maryam Seyedsaleki (2012) proved that organic culture, environmental concern, price, subjective norms, quality and familiarity affect attitudes and thereby purchasing organic  ... 
fatcat:qyt2pyxkcbd6vpqxh7jlatu6cy
« Previous Showing results 1 — 15 out of 17 results