The impact of the soft errors in convolutional neural network on GPUs: Alexnet as case study

Adam, Khalid; Mohd, Izzeldin I.; Younis, Younis M.

doi:10.1016/j.procs.2021.02.012

Cited by 15 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model was presented by Simonyan and Zisserman from the University of Oxford [ 28 ] and was one of the famous models submitted to ILSVRC-2014 [ 29 ]. This model replaces the large kernel-sized filters of AlexNet [ 30 ] with multiple small-size (3 × 3) kernels to improve the accuracy. Like VGGFace, the input to conv1 layer in VGG16 is fixed to 224 × 224 RGB image.…”

Section: Frameworkmentioning

confidence: 99%

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

Goel

Mehmood

Ugail

2021

Sensors

View full text Add to dashboard Cite

Accurate identification of siblings through face recognition is a challenging task. This is predominantly because of the high degree of similarities among the faces of siblings. In this study, we investigate the use of state-of-the-art deep learning face recognition models to evaluate their capacity for discrimination between sibling faces using various similarity indices. The specific models examined for this purpose are FaceNet, VGGFace, VGG16, and VGG19. For each pair of images provided, the embeddings have been calculated using the chosen deep learning model. Five standard similarity measures, namely, cosine similarity, Euclidean distance, structured similarity, Manhattan distance, and Minkowski distance, are used to classify images looking for their identity on the threshold defined for each of the similarity measures. The accuracy, precision, and misclassification rate of each model are calculated using standard confusion matrices. Four different experimental datasets for full-frontal-face, eyes, nose, and forehead of sibling pairs are constructed using publicly available HQf subset of the SiblingDB database. The experimental results show that the accuracy of the chosen deep learning models to distinguish siblings based on the full-frontal-face and cropped face areas vary based on the face area compared. It is observed that VGGFace is best while comparing the full-frontal-face and eyes—the accuracy of classification being with more than 95% in this case. However, its accuracy degrades significantly when the noses are compared, while FaceNet provides the best result for classification based on the nose. Similarly, VGG16 and VGG19 are not the best models for classification using the eyes, but these models provide favorable results when foreheads are compared.

show abstract

Section: Frameworkmentioning

confidence: 99%

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

Goel

Mehmood

Ugail

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The benefit is that it uses GPU for preparation and executing activities. In deep neural networks, AlexNet also acts as a starting point in computer vision and voice recognition [62][63]. As shown in Fig.…”

Section: Alexnetmentioning

confidence: 99%

Skin Lesions Classification Using Deep Learning Techniques: Review

Kareem

Abdulazeez

Zeebaree

2021

AJRCoS

View full text Add to dashboard Cite

Skin cancer is a significant health problem. More than 123,000 new cases per year are recorded. Melanoma is the most popular type of skin cancer, leading to more than 9000 deaths annually in the USA. Skin disease diagnosis is getting difficult due to visual similarities. While Melanoma is the most common form of skin cancer, other pathology types are also fatal. Automatic melanoma screening systems will be useful in identifying those skin cancers more appropriately. Advances in technology and growth in computational capabilities have allowed machine learning and deep learning algorithms to analyze skin lesion images. Deep Convolutional Neural Networks (DCNNs) have achieved more encouraging results, yet faster systems for diagnosing fatal diseases are the need of the hour. This paper presents a survey of techniques for skin cancer detection from images. The paper aims to present a review of existing state-of-the-art and effective models for automatically detecting Melanoma from skin images. The result of classifications and segmentation from the skin lesion images will be processed better using the ensemble deep learning algorithm.

show abstract

“…Because of the huge various parameters, convolutional neural networks (CNNs) may readily overfit on small datasets; hence, generalization effectiveness is related to the amount of labeled data [14]. CNN uses a hierarchical design to automatically extract deep features, which is particularly successful in a variety of visual applications and tasks including image denoising and object recognition [15], then classification [16]. Many research projects have been carried out intensely and rapidly to create artificial intelligence (AI) techniques for reacting to the COVID-19 global outbreak.…”

Section: Introductionmentioning

confidence: 99%

COVID-19 detection based on convolution neural networks from CT-scan images: a review

Ibrahim

Mahmood²

2023

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">The COVID-19 outbreak has been affecting the health of people all around the world. With the number of confirmed cases and deaths still rising daily, so the main aim is to detect positive cases as soon as and provide them with the necessary treatment. The utilization of imaging data including chest x-rays and computed tomography (CT) was proven that is would be beneficial for quickly diagnosing COVID-19. Since Computerized Tomography provides a huge number of images, recognizing these visual traits would be difficult and take enormous amounts of time for radiologists so automated diagnosis technologies including deep learning (DL) models are recently for COVID-19 screening in CT scans. This review paper presents different researches which used deep learning approaches including various models of convolutional neural networks (CNN) used in image classification tasks well, and large training, like ResNet, VGG, AlexNet, LeNet, GoogleNet, and others for COVID-19 diagnosing and severity assessments using chest CT images. As a result, automated COVID-19 analysis on CT images is essential to save medical personnel and essential time for disease prevention.</span>

show abstract

The impact of the soft errors in convolutional neural network on GPUs: Alexnet as case study

Cited by 15 publications

References 18 publications

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

A Study of Deep Learning-Based Face Recognition Models for Sibling Identification

Skin Lesions Classification Using Deep Learning Techniques: Review

COVID-19 detection based on convolution neural networks from CT-scan images: a review

Contact Info

Product

Resources

About