با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
Learning in the machine: To share or not to share?
یادگیری در دستگاه: برای به اشتراک گذاشتن یا عدم اشتراک گذاری؟-2020 Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes.
However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy
raises the fundamental question of whether weight-sharing is necessary. If so, to which degree of
precision? If not, what are the alternatives? The goal of this study is to investigate these questions,
primarily through simulations where the weight-sharing assumption is relaxed. Taking inspiration
from neural circuitry, we explore the use of Free Convolutional Networks and neurons with variable
connection patterns. Using Free Convolutional Networks, we show that while weight-sharing is a
pragmatic optimization approach, it is not a necessity in computer vision applications. Furthermore,
Free Convolutional Networks match the performance observed in standard architectures when trained
using properly translated data (akin to video). Under the assumption of translationally augmented data,
Free Convolutional Networks learn translationally invariant representations that yield an approximate
form of weight-sharing. Keywords: Deep learning | Convolutional neural networks | Weight-sharing | Biologically plausible architectures |
مقاله انگلیسی |
2 |
Sparse low rank factorization for deep neural network compression
فاکتورسازی رتبه پراکنده برای فشرده سازی شبکه عصبی عمیق-2020 Storing and processing millions of parameters in deep neural networks is highly challenging during the deployment of model in real-time application on resource constrained devices. Popular low-rank approx- imation approach singular value decomposition (SVD) is generally applied to the weights of fully con- nected layers where compact storage is achieved by keeping only the most prominent components of the decomposed matrices. Years of research on pruning-based neural network model compression re- vealed that the relative importance or contribution of each neuron in a layer highly vary among each other. Recently, synapses pruning has also demonstrated that having sparse matrices in network archi- tecture achieve lower space and faster computation during inference time. We extend these arguments by proposing that the low-rank decomposition of weight matrices should also consider significance of both input as well as output neurons of a layer. Combining the ideas of sparsity and existence of un- equal contributions of neurons towards achieving the target, we propose sparse low rank (SLR) method which sparsifies SVD matrices to achieve better compression rate by keeping lower rank for unimportant neurons. We demonstrate the effectiveness of our method in compressing famous convolutional neural networks based image recognition frameworks which are trained on popular datasets. Experimental re- sults show that the proposed approach SLR outperforms vanilla truncated SVD and a pruning baseline, achieving better compression rates with minimal or no loss in the accuracy. Code of the proposed ap- proach is avaialble at https://github.com/sridarah/slr . Keywords: Low-rank approximation | Singular value decomposition | Sparse matrix | Deep neural networks | Convolutional neural networks |
مقاله انگلیسی |
3 |
A survey on deep learning based face recognition
مروری بر شناخت چهره مبتنی بر یادگیری عمیق-2019 Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face
recognition recently, and a number of deep learning methods have been proposed. This paper summarizes
about 330 contributions in this area. It reviews major deep learning concepts pertinent to face image analysis
and face recognition, and provides a concise overview of studies on specific face recognition problems, such
as handling variations in pose, age, illumination, expression, and heterogeneous face matching. A summary
of databases used for deep face recognition is given as well. Finally, some open challenges and directions are
discussed for future research. Keywords: Deep learning | Face recognition | Artificial Neural Network | Convolutional Neural Networks | Autoencoder | Generative Adversarial Networks |
مقاله انگلیسی |
4 |
Deep learning-assisted literature mining for in vitro radiosensitivity data
استخراج ادبیات با کمک یادگیری عمیق برای داده های تابش آزمایشگاهی -2019 Background and purpose: Integrated analysis of existing radiosensitivity data obtained by the goldstandard
clonogenic assay has the potential to improve our understanding of cancer cell radioresistance.
However, extraction of radiosensitivity data from the literature is highly labor-intensive. To aid in this
task, using deep convolutional neural networks (CNNs) and other computer technologies, we developed
an analysis pipeline that extracts radiosensitivity data derived from clonogenic assays from the literature.
Materials and methods: Three classifiers (C1–3) were developed to identify publications containing
radiosensitivity data derived from clonogenic assays. C1 uses Faster Regions CNN with Inception
Resnet v2 (fRCNN-IRv2), VGG-16, and Optical Character Recognition (OCR) to identify publications that
contain semi-logarithmic graphs showing radiosensitivity data derived from clonogenic assays. C2 uses
fRCNN-IRv2 and OCR to identify publications that contain bar graphs showing radiosensitivity data
derived from clonogenic assays. C3 is a program that identifies publications containing keywords related
to radiosensitivity data derived from clonogenic assays. A program (iSF2) was developed using Mask
RCNN and OCR to extract surviving fraction after 2-Gy irradiation (SF2) as assessed by clonogenic assays,
presented in semi-logarithmic graphs. The efficacy of C1–3 and iSF2 was tested using seven datasets
(1805 and 222 publications in total, respectively).
Results: C1–3 yielded sensitivity of 91.2% ± 3.4% and specificity of 90.7% ± 3.6%. iSF2 returned SF2 values
that were within 2.9% ± 2.6% of the SF2 values determined by radiation oncologists.
Conclusion: Our analysis pipeline is potentially useful to acquire radiosensitivity data derived from clonogenic
assays from the literature. Keywords: Clonogenic assays | Radiosensitivity | Deep learning | Convolutional neural networks | Radiation oncology |
مقاله انگلیسی |
5 |
Establishing structure-property localization linkages for elastic deformation of three-dimensional high contrast composites using deep learning approaches
ایجاد پیوندهای محلی سازی ساختار و خاصیت برای تغییر شکل الاستیک کامپوزیت های کنتراست بالا سه بعدی با استفاده از روشهای یادگیری عمیق-2019 Data-driven methods are attracting growing attention in the field of materials science. In particular, it is
now becoming clear that machine learning approaches offer a unique avenue for successfully mining
practically useful process-structure-property (PSP) linkages from a variety of materials data. Most previous
efforts in this direction have relied on feature design (i.e., the identification of the salient features
of the material microstructure to be included in the PSP linkages). However due to the rich complexity of
features in most heterogeneous materials systems, it has been difficult to identify a set of consistent
features that are transferable from one material system to another. With flexible architecture and
remarkable learning capability, the emergent deep learning approaches offer a new path forward that
circumvents the feature design step. In this work, we demonstrate the implementation of a deep learning
feature-engineering-free approach to the prediction of the microscale elastic strain field in a given threedimensional
voxel-based microstructure of a high-contrast two-phase composite. The results show that
deep learning approaches can implicitly learn salient information about local neighborhood details, and
significantly outperform state-of-the-art methods. Keywords: Materials informatics | Convolutional neural networks | Deep learning | Localization | Structure-property linkages |
مقاله انگلیسی |
6 |
Differential convolutional neural network
شبکه های عصبی تکاملی دیفرانسیلی-2019 Convolutional neural networks with strong representation ability of deep structures have ever increasing
popularity in many research areas. The main difference of Convolutional Neural Networks
with respect to existing similar artificial neural networks is the inclusion of the convolutional part.
This inclusion directly increases the performance of artificial neural networks. This fact has led to the
development of many different convolutional models and techniques.
In this work, a novel convolution technique named as Differential Convolution and updated
error back-propagation algorithm is proposed. The proposed technique aims to transfer feature maps
containing directional activation differences to the next layer. This implementation takes the idea
of how convolved features change on the feature map into consideration. In a sense, this process
adapts the mathematical differentiation operation into the convolutional process. Proposed improved
back propagation algorithm also considers neighborhood activation errors. This property increases the
classification performance without changing the number of filters.
Four different experiment sets were performed to observe the performance and the adaptability
of the differential convolution technique. In the first experiment set utilization of the differential
convolution on a traditional convolutional neural network structure made a performance boost up
to 55.29% for the test accuracy. In the second experiment set differential convolution adaptation
raised the top1 and top5 test accuracies of AlexNet by 5.3% and 4.75% on ImageNet dataset. In the
third experiment set differential convolution utilized model outperformed all compared convolutional
structures. In the fourth experiment set, the Differential VGGNet model obtained by adapting proposed
differential convolution technique performed 93.58% and 75.06% accuracy values for CIFAR10 and CIFAR100
datasets, respectively. The accuracy values of the Differential NIN model containing differential
convolution operation were 92.44% and 72.65% for the same datasets. In these experiment sets, it was
observed that the differential convolution technique outperformed both traditional convolution and
other compared convolution techniques. In addition, easy adaptation of the proposed technique to
different convolutional structures and its efficiency demonstrate that popular deep learning models
may be improved with differential convolution Keywords: Convolutional neural networks | Deep learning | Image classification | Convolution techniques | Pattern recognition | Machine learning |
مقاله انگلیسی |
7 |
Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding
تشخیص نقص تصویر جوش تشخیص عمیق مبتنی بر یادگیری عمیق برخط با استفاده از شبکه های عصبی همگرا برای آلیاژ آل در جوش قوس رباتیک-2019 Accurate on-line weld defects detection is still challenging for robotic welding manufacturing due to the complexity
of weld defects. This paper studied deep learning–based on-line defects detection for aluminum alloy in robotic arc
welding using Convolutional Neural Networks (CNN) and weld images. Firstly, an image acquisition system was
developed to simultaneously collect weld images, which can provide more information of the real-time weld images
from different angles including top front, top back and back seam. Then, a new CNN classification model with 11
layers based on weld image was designed to identify weld penetration defects. In order to improve the robustness and
generalization ability of the CNN model, weld images from different welding current and feeding speed were captured
for the CNN model. Based on the actual industry challenges such as the instability of welding arc, the complexity
of the welding environment and the random changing of plate gap condition, two kinds of data augmentation
including noise adding and image rotation were used to boost the CNN dataset while parameters optimization was
carried out. Finally, non-zero pixel method was proposed to quantitatively evaluate and visualize the deep learning
features. Furthermore, their physical meaning were clearly explained. Instead of decreasing the interference from arc
light as in traditional way, the CNN model has taken full use of those arc lights by combining them in a various way
to form the complementary features. Test results shows that the CNN model has better performance than our previous
work with the mean classification accuracy of 99.38%. This paper can provide some guidance for on-line
detection of manufacturing quality in metal additive manufacturing (AM) and laser welding. Keywords: Deep learning | Defects detection | Al alloy | Robotic arc welding | Convolutional neural networks | Weld images | Feature visualization |
مقاله انگلیسی |
8 |
Deep learning based predictive modeling for structure-property linkages
مدل سازی پیش بینی مبتنی بر یادگیری عمیق برای پیوندهای ساختار و ویژگی-2019 Crystal plasticity finite element method (CPFEM) based simulations have been traditionally used for analyses of deformation in metals. However, CPFEM simulations are computationally expensive, especially for problems like fatigue where analyses are based on deformation cycles. Moreover, correlations of structure-property linkages based on homogenization and localization are not easily conceived. In this work deep learning based models have been proposed that are able to predict macroscopic properties based on features extracted from the microstructure with minimal human bias. The model is able to predict property against a given structure within dual phase, isotropic elastic-plastic regime. A systematic approach for finding optimal depth and width of neural network has been identified that reduces the overall development effort. It is observed that in the absence of a large training dataset, performance of a convolutional neural network (CNN) model degrades if too many layers and/or too many neurons are used. The CNN model is able to identify soft and hard regions of microstructures and is able to correlate structure-property relation in forward sense i.e. for homogenization. In this work, it has been demonstrated that human intervention is not needed for feature extraction and selection leading to minimization of researcher’s bias. The drawback of CNN model interpretability is overcome by using Respond-CAM feature visualization. Keywords: Machine learning | Crystal plasticity | Convolutional neural networks | Micromechanics | Deep learning | ICME |
مقاله انگلیسی |
9 |
DeepOtsu: Document enhancement and binarization using iterative deep learning
DeepOtsu: تقویت و باینری سازی اسناد با استفاده از یادگیری عمیق تکراری-2019 This paper presents a novel iterative deep learning framework and applies it to document enhancement and binarization. Unlike the traditional methods that predict the binary label of each pixel on the input image, we train the neural network to learn the degradations in document images and produce uniform images of the degraded input images, which in turn allows the network to refine the output iteratively. Two different iterative methods have been studied in this paper: recurrent refinement (RR) that uses the same trained neural network in each iteration for document enhancement and stacked refinement (SR) that uses a stack of different neural networks for iterative output refinement. Given the learned nature of the uniform and enhanced image, the binarization map can be easily obtained through use of a global or local threshold. The experimental results on several public benchmark data sets show that our proposed method provides a new, clean version of the degraded image, one that is suitable for visualization and which shows promising results for binarization using Otsu’s global threshold, based on enhanced images learned iteratively by the neural network. Keywords: Document enhancement and binarization | Convolutional neural networks | Iterative deep learning | Recurrent refinement |
مقاله انگلیسی |
10 |
A comparative study of deep learning architectures on melanoma detection
مطالعه تطبیقی معماریهای یادگیری عمیق در تشخیص ملانوما-2019 Melanoma is the most aggressive type of skin cancer, which significantly reduces the life expectancy. Early
detection of melanoma can reduce the morbidity and mortality associated with skin cancer. Dermoscopic images
acquired by dermoscopic instruments are used in computational analysis for skin cancer detection. However,
some image quality limitations such as noises, shadows, artefacts exist that could compromise the robustness of
the skin image analysis. Hence, developing an automatic intelligent system for skin cancer diagnosis with accurate
detection rate is crucial. In this paper, we evaluate the performance of several state-of-the-art convolutional
neural networks in dermoscopic images of skin lesions. Our experiment is conducted on a graphics processing
unit (GPU) to speed up the training and deployment process. To enhance the quality of images, we
employ different pre-processing steps. We also apply data augmentation methodology such as horizontal and
vertical flipping techniques to address the class skewness problem. Both pre-processing and data augmentation
could help to improve the final accuracy. Keywords: Cancer classification | Computational diagnosis | Convolutional neural networks | Deep learning | Melanoma detection |
مقاله انگلیسی |