چند روز پیش مقاله خیلی جالبی در حوزه یادگیری عمیق برای segmentation ارایه شد که می خوانیم:
Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results.
لینک مقاله
#معرفی_مقاله #یادگیری_عمیق #segmentation
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Obtaining an accurate segmentation of images obtained by computed microtomography (micro-CT) techniques is a non-trivial process due to the wide range of noise types and artifacts present in these images. Current methodologies are often time-consuming, sensitive to noise and artifacts, and require skilled people to give accurate results. Motivated by the rapid advancement of deep learning-based segmentation techniques in recent years, we have developed a tool that aims to fully automate the segmentation process in one step, without the need for any extra image processing steps such as noise filtering or artifact removal. To get a general model, we train our network using a dataset made of high-quality three-dimensional micro-CT images from different scanners, rock types, and resolutions. In addition, we use a domain-specific augmented training pipeline with various types of noise, synthetic artifacts, and image transformation/distortion. For validation, we use a synthetic dataset to measure accuracy and analyze noise/artifact sensitivity. The results show a robust and accurate segmentation performance for the most common types of noises present in real micro-CT images. We also compared the segmentation of our method and five expert users, using commercial and open software packages on real rock images. We found that most of the current tools fail to reduce the impact of local and global noises and artifacts. We quantified the variation on human-assisted segmentation results in terms of physical properties and observed a large variation. In comparison, the new method is more robust to local noises and artifacts, outperforming the human segmentation and giving consistent results. Finally, we compared the porosity of our model segmented images with experimental porosity measured in the laboratory for ten different untrained samples, finding very encouraging results.
لینک مقاله
#معرفی_مقاله #یادگیری_عمیق #segmentation
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Nature
Automatic segmentation tool for 3D digital rocks by deep learning
Scientific Reports - Automatic segmentation tool for 3D digital rocks by deep learning
مقاله A tiny deep capsule network
شبکه ای که به تازگی ارایه شد و قابلیت استفاده در زمینه های متفاوت را دارد. خواندن این مقاله بسیار توصیه می شود.
The capsule network (CapsNet) is a novel network model that can learn spatial information in images. However, the performance of CapsNet on complex datasets (such as CIFAR10) is limited and it requires a large number of parameters. These disadvantages make CapsNet less useful, especially in some resource-constrained devices. To solve this problem, we propose a novel tiny deep capsule architecture (CapsInfor), which consists of many fast tensor capsule layers (FastCaps) with a novel routing process. CapsInfor requires only a few parameters to achieve satisfactory performance. For example, on CIFAR10, the accuracy of CapsInfor is 9.32% higher than that of CapsNet, but the parameters are reduced by 97.53%. CapsInfor is composed of multiple pipelines each of which processes a kind of image information. To achieve information interaction between pipelines, a novel cross node is proposed to implement pipeline-level capsule routing. A new decision maker is used to analyze the predicted values of pipelines and gives the final classification result. Using these proposed methods, CapsInfor achieves competitive results on CIFAR10, CIFAR100, FMNIST, and SVHN. Besides, it is proved that CapsInfor has satisfactory affine robustness on affNIST. To alleviate the problem that the parameter explosion with increasing the number of classes, a novel two-level classification method is proposed. This method can effectively reduce the parameters of the model on the 10 categories and 100 categories tasks. The experimental results confirm that CapsInfor is a tiny deep capsule model with satisfactory classification accuracy and affine robustness.
#یادگیری_عمیق #معرفی_مقاله #capsule_network
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
شبکه ای که به تازگی ارایه شد و قابلیت استفاده در زمینه های متفاوت را دارد. خواندن این مقاله بسیار توصیه می شود.
The capsule network (CapsNet) is a novel network model that can learn spatial information in images. However, the performance of CapsNet on complex datasets (such as CIFAR10) is limited and it requires a large number of parameters. These disadvantages make CapsNet less useful, especially in some resource-constrained devices. To solve this problem, we propose a novel tiny deep capsule architecture (CapsInfor), which consists of many fast tensor capsule layers (FastCaps) with a novel routing process. CapsInfor requires only a few parameters to achieve satisfactory performance. For example, on CIFAR10, the accuracy of CapsInfor is 9.32% higher than that of CapsNet, but the parameters are reduced by 97.53%. CapsInfor is composed of multiple pipelines each of which processes a kind of image information. To achieve information interaction between pipelines, a novel cross node is proposed to implement pipeline-level capsule routing. A new decision maker is used to analyze the predicted values of pipelines and gives the final classification result. Using these proposed methods, CapsInfor achieves competitive results on CIFAR10, CIFAR100, FMNIST, and SVHN. Besides, it is proved that CapsInfor has satisfactory affine robustness on affNIST. To alleviate the problem that the parameter explosion with increasing the number of classes, a novel two-level classification method is proposed. This method can effectively reduce the parameters of the model on the 10 categories and 100 categories tasks. The experimental results confirm that CapsInfor is a tiny deep capsule model with satisfactory classification accuracy and affine robustness.
#یادگیری_عمیق #معرفی_مقاله #capsule_network
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
SpringerLink
A tiny deep capsule network
International Journal of Machine Learning and Cybernetics - The capsule network (CapsNet) is a novel network model that can learn spatial information in images. However, the performance of CapsNet...
لینک کامیونیتی های Stack Exchange که برای یادگیری عمیق مفید هستند:
🟢 AI
🟢 Data Science
🟢 Cross Validated
🟢 Computer Science
🟢 Mathematics
🟢 Robotics
🟢 Signal Processing
🟢 Stack Overflow
لینک کامیونیتی های Stack Exchange که برای نوشتن مقاله مناسب هستند:
🔴 Academia
🔴 LaTeX
لینک کامیونیتی های Stack Exchange که برای تقویت زبان انگلیسی مناسب هستند:
🟡 English Language & Usage
🟡 English Language Learners
#معرفی_منبع #معرفی_منبع_آموزش #زبان #یادگیری_عمیق #stackexchange
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
🟢 AI
🟢 Data Science
🟢 Cross Validated
🟢 Computer Science
🟢 Mathematics
🟢 Robotics
🟢 Signal Processing
🟢 Stack Overflow
لینک کامیونیتی های Stack Exchange که برای نوشتن مقاله مناسب هستند:
🔴 Academia
🔴 LaTeX
لینک کامیونیتی های Stack Exchange که برای تقویت زبان انگلیسی مناسب هستند:
🟡 English Language & Usage
🟡 English Language Learners
#معرفی_منبع #معرفی_منبع_آموزش #زبان #یادگیری_عمیق #stackexchange
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Stackexchange
Hot Questions - Stack Exchange
We make Stack Overflow and 170+ other community-powered Q&A sites.
در ادامه لینک مقاله روشهای افزایش دیتا برای تصاویر را قرار می دهیم. این مقاله روشهای متفاوتی را بررسی کرده است. افزایش داده یکی از راهکارها برای افزایش قدرت تعمیم شبکه های عصبی است.
A survey on Image Data Augmentation for Deep Learning
Depp convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them. The image augmentation algorithms discussed in this survey include geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks, neural style transfer, and meta-learning. The application of augmentation methods based on GANs are heavily covered in this survey. In addition to augmentation techniques, this paper will briefly discuss other characteristics of Data Augmentation such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing Data Augmentation. Readers will understand how Data Augmentation can improve the performance of their models and expand limited datasets to take advantage of the capabilities of big data.
#معرفی_مقاله #بینایی_ماشین #data_augmentation #مقاله_مروری
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
A survey on Image Data Augmentation for Deep Learning
Depp convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality of training datasets such that better Deep Learning models can be built using them. The image augmentation algorithms discussed in this survey include geometric transformations, color space augmentations, kernel filters, mixing images, random erasing, feature space augmentation, adversarial training, generative adversarial networks, neural style transfer, and meta-learning. The application of augmentation methods based on GANs are heavily covered in this survey. In addition to augmentation techniques, this paper will briefly discuss other characteristics of Data Augmentation such as test-time augmentation, resolution impact, final dataset size, and curriculum learning. This survey will present existing methods for Data Augmentation, promising developments, and meta-level decisions for implementing Data Augmentation. Readers will understand how Data Augmentation can improve the performance of their models and expand limited datasets to take advantage of the capabilities of big data.
#معرفی_مقاله #بینایی_ماشین #data_augmentation #مقاله_مروری
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
مقاله جالبی که چند روز پیش برای خودروهای خودران چاپ شد که سبب می شود خودرو بین خطوط حرکت کند.
Visual Autopilot Decision System Based on Deep Learning
The development of artificial intelligence and automatic driving is in full swing, and the application of artificial intelligence technology in automatic driving technology is becoming more and more in-depth. Therefore, this paper proposes a visual automatic driving decision system based on deep learning, which can make automatic driving vehicles keep straight in the lane.
#یادگیری_عمیق #self_driving_car #معرفی_مقاله #visual_autopilot
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Visual Autopilot Decision System Based on Deep Learning
The development of artificial intelligence and automatic driving is in full swing, and the application of artificial intelligence technology in automatic driving technology is becoming more and more in-depth. Therefore, this paper proposes a visual automatic driving decision system based on deep learning, which can make automatic driving vehicles keep straight in the lane.
#یادگیری_عمیق #self_driving_car #معرفی_مقاله #visual_autopilot
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
SpringerLink
Visual Autopilot Decision System Based on Deep Learning
The development of artificial intelligence and automatic driving is in full swing, and the application of artificial intelligence technology in automatic driving technology is becoming more and more...
یکی از تحولات سالهای اخیر شبکه های عصبی، بعد از چاپ مقاله کپسول دکتر هینتون بود. چند روز پیش مقاله A Few-Shot Learning-Based Siamese Capsule Network for Intrusion Detection with Imbalanced Training Data چاپ شد که براساس همین ایده است. کاربردهای شبکه های کپسول به علت دید متفاوت و درست تر نسبت به شبکه های کانولوشنی، بسیار بالاست.
Network intrusion detection remains one of the major challenges in cybersecurity. In recent years, many machine-learning-based
methods have been designed to capture the dynamic and complex intrusion patterns to improve the performance of intrusion
detection systems. However, two issues, including imbalanced training data and new unknown attacks, still hinder the development of a reliable network intrusion detection system. In this paper, we propose a novel few-shot learning-based Siamese
capsule network to tackle the scarcity of abnormal network traffic training data and enhance the detection of unknown attacks. In
specific, the well-designed deep learning network excels at capturing dynamic relationships across traffic features. In addition, an
unsupervised subtype sampling scheme is seamlessly integrated with the Siamese network to improve the detection of network
intrusion attacks under the circumstance of imbalanced training data. Experimental results have demonstrated that the metric
learning framework is more suitable to extract subtle and distinctive features to identify both known and unknown attacks after
the sampling scheme compared to other supervised learning methods. Compared to the state-of-the-art methods, our proposed
method achieves superior performance to effectively detect both types of attacks.
#یادگیری_عمیق #capsule_network #معرفی_مقاله #siamese_network
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Network intrusion detection remains one of the major challenges in cybersecurity. In recent years, many machine-learning-based
methods have been designed to capture the dynamic and complex intrusion patterns to improve the performance of intrusion
detection systems. However, two issues, including imbalanced training data and new unknown attacks, still hinder the development of a reliable network intrusion detection system. In this paper, we propose a novel few-shot learning-based Siamese
capsule network to tackle the scarcity of abnormal network traffic training data and enhance the detection of unknown attacks. In
specific, the well-designed deep learning network excels at capturing dynamic relationships across traffic features. In addition, an
unsupervised subtype sampling scheme is seamlessly integrated with the Siamese network to improve the detection of network
intrusion attacks under the circumstance of imbalanced training data. Experimental results have demonstrated that the metric
learning framework is more suitable to extract subtle and distinctive features to identify both known and unknown attacks after
the sampling scheme compared to other supervised learning methods. Compared to the state-of-the-art methods, our proposed
method achieves superior performance to effectively detect both types of attacks.
#یادگیری_عمیق #capsule_network #معرفی_مقاله #siamese_network
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
چند روز پیش مقاله ای ارایه شد برای بهبود تصاویر JPEG که می خوانیم:
With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.
لینک مقاله
#معرفی_مقاله #یادگیری_عمیق #بینایی_ماشین
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.
لینک مقاله
#معرفی_مقاله #یادگیری_عمیق #بینایی_ماشین
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
A New Deep Learning Engine for CoralNet
CoralNet is a cloud-based website and platform for manual, semi-automatic and automatic analysis of coral reef images. Users access CoralNet through optimized webbased workflows for common tasks, and other systems can interface through API’s. Today, marine scientists are widely using CoralNet, and nearly 3,000 registered users have uploaded 1,741,855 images from 2,040 distinct sources with over 65 million annotations. CoralNet is hosted on AWS, is free for users, and the code is open source 1. In January 2021, we released CoralNet 1.0 which has a new machine learning engine. This paper provides an overview of that engine, and the process of choosing the particular architecture, its training, and a comparison to some of the most promising architectures. In a nutshell, CoralNet 1.0 uses transfer learning with an EfficientNet-B0 backbone that is trained on 16M labelled patches from benthic images and a hierarchical Multi-layer Perceptron classifier that is trained on source-specific labelled data. When evaluated on a holdout test set of 26 sources, the error rate of CoralNet 1.0 was 18.4% (relative) lower than CoralNet Beta.
#معرفی_مقاله #یادگیری_عمیق #بینایی_ماشین #coral_net
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
CoralNet is a cloud-based website and platform for manual, semi-automatic and automatic analysis of coral reef images. Users access CoralNet through optimized webbased workflows for common tasks, and other systems can interface through API’s. Today, marine scientists are widely using CoralNet, and nearly 3,000 registered users have uploaded 1,741,855 images from 2,040 distinct sources with over 65 million annotations. CoralNet is hosted on AWS, is free for users, and the code is open source 1. In January 2021, we released CoralNet 1.0 which has a new machine learning engine. This paper provides an overview of that engine, and the process of choosing the particular architecture, its training, and a comparison to some of the most promising architectures. In a nutshell, CoralNet 1.0 uses transfer learning with an EfficientNet-B0 backbone that is trained on 16M labelled patches from benthic images and a hierarchical Multi-layer Perceptron classifier that is trained on source-specific labelled data. When evaluated on a holdout test set of 26 sources, the error rate of CoralNet 1.0 was 18.4% (relative) lower than CoralNet Beta.
#معرفی_مقاله #یادگیری_عمیق #بینایی_ماشین #coral_net
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
از یادگیری عمیق تقویتی می توان در navigation استفاده کرد. این ناوبری لزوما در خودروهای خودران نیست! چند روز پیش مقاله ای با نتایج مناسبی چاپ شد که در ادامه می خوانیم:
DEEP REINFORCEMENT LEARNING FOR GUIDEWIRE NAVIGATION IN CORONARY ARTERY PHANTOM
In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning (RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human demonstrations with deep Q-learning from demonstrations (DQfD), transfer learning, and weight initialization. ‘State’ for RL is customized as a focus window near the guidewire tip, and subgoals are placed to mitigate a sparse reward problem. The RL agent improves performance, eventually enabling the guidewire to reach all valid targets in ‘stable’ phase. Our framework opens a new direction in the automation of robot-assisted intervention, providing guidance on RL in physical spaces involving mechanical fatigue.
#یادگیری_عمیق #یادگیری_عمیق_تقویتی #معرفی_مقاله #navigation
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
DEEP REINFORCEMENT LEARNING FOR GUIDEWIRE NAVIGATION IN CORONARY ARTERY PHANTOM
In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning (RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human demonstrations with deep Q-learning from demonstrations (DQfD), transfer learning, and weight initialization. ‘State’ for RL is customized as a focus window near the guidewire tip, and subgoals are placed to mitigate a sparse reward problem. The RL agent improves performance, eventually enabling the guidewire to reach all valid targets in ‘stable’ phase. Our framework opens a new direction in the automation of robot-assisted intervention, providing guidance on RL in physical spaces involving mechanical fatigue.
#یادگیری_عمیق #یادگیری_عمیق_تقویتی #معرفی_مقاله #navigation
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
در ICCV امسال (2021) مقاله مهمی تحت عنوان MUSIQ: Multi-scale Image Quality Transformer ارایه شده که پیرامون image quality assessment است. این زمینه در حوزه computer vision بسیار پر کاربرد است. در این مقاله می خوانیم:
Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scale image representation, our proposed method can capture image quality at different granularities. Furthermore, a novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation. Experimental results verify that our method can achieve state-of-the-art performance on multiple large scale IQA datasets such as PaQ-2-PiQ, SPAQ, and KonIQ-10k.
#معرفی_مقاله #یادگیری_عمیق #transformer #بینایی_ماشین #IQA
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Image quality assessment (IQA) is an important research topic for understanding and improving visual experience. The current state-of-the-art IQA methods are based on convolutional neural networks (CNNs). The performance of CNN-based models is often compromised by the fixed shape constraint in batch training. To accommodate this, the input images are usually resized and cropped to a fixed shape, causing image quality degradation. To address this, we design a multi-scale image quality Transformer (MUSIQ) to process native resolution images with varying sizes and aspect ratios. With a multi-scale image representation, our proposed method can capture image quality at different granularities. Furthermore, a novel hash-based 2D spatial embedding and a scale embedding is proposed to support the positional embedding in the multi-scale representation. Experimental results verify that our method can achieve state-of-the-art performance on multiple large scale IQA datasets such as PaQ-2-PiQ, SPAQ, and KonIQ-10k.
#معرفی_مقاله #یادگیری_عمیق #transformer #بینایی_ماشین #IQA
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Media is too big
VIEW IN TELEGRAM
Rich Sutton & Andy Barto
Two Genius Minds in Deep Reinforcement Learning
#بزرگان #یادگیری_عمیق_تقویتی #یادگیری_عمیق #یادگیری_تقویتی #ساتون #بارتو #ویدیو
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Two Genius Minds in Deep Reinforcement Learning
#بزرگان #یادگیری_عمیق_تقویتی #یادگیری_عمیق #یادگیری_تقویتی #ساتون #بارتو #ویدیو
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
در ادامه لینکی از دیتاستهای کاربردی قرار می گیرد.
Datasets for Data Mining, Data Science, and Machine Learning
#معرفی_منبع #دیتاست #یادگیری_ماشین #یادگیری_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Datasets for Data Mining, Data Science, and Machine Learning
#معرفی_منبع #دیتاست #یادگیری_ماشین #یادگیری_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
KDnuggets
Datasets for Data Science, Machine Learning, AI & Analytics - KDnuggets
KDnuggets subscribers now have access to the WorldData.AI Partners Plan at no cost! Check out the world’s largest external curated data platform, integrating data from all leading global sources. Data Repositories Anacode Chinese Web Datastore: A collection…
Welcome to the UC Irvine Machine Learning Repository!
We currently maintain 588 data sets as a service to the machine learning community. You may view all data sets through our searchable interface. For a general overview of the Repository, please visit our About page. For information about citing data sets in publications, please read our citation policy. If you wish to donate a data set, please consult our donation policy. For any other questions, feel free to contact the Repository librarians.
#معرفی_منبع #دیتاست #یادگیری_ماشین #یادگیری_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
We currently maintain 588 data sets as a service to the machine learning community. You may view all data sets through our searchable interface. For a general overview of the Repository, please visit our About page. For information about citing data sets in publications, please read our citation policy. If you wish to donate a data set, please consult our donation policy. For any other questions, feel free to contact the Repository librarians.
#معرفی_منبع #دیتاست #یادگیری_ماشین #یادگیری_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Telegram
Bias Variance
🌴 سایت:
https://biasvariance.net
🌺 کانال تلگرام:
@biasvariance_ir
🌳 پشتیبانی:
@biasvariance
🌷 اینستاگرام:
https://www.instagram.com/bvariance/
https://biasvariance.net
🌺 کانال تلگرام:
@biasvariance_ir
🌳 پشتیبانی:
@biasvariance
🌷 اینستاگرام:
https://www.instagram.com/bvariance/
یکی از زمینه های پرکاربرد در computer vision دیتکشن (detection) است. از کاربردهای عملی این موضوع می توان به پیدا کردن تابلوهای راهنمایی و رانندگی اشاره کرد که زمینه فعالیت مناسبی در حوزه یادگیری عمیق است. در ادامه مقاله ای که چند روز پیش در این زمینه چاپ شد را مشاهده می کنید.
A Deep Learning-Based Residual Network Model for Traffic Sign Detection and Classification
Traffic sign board recognition is a very significant work for the upcoming driver assistance intelligent vehicle systems. The ability to detect such traffic signs from the real road scenes intensifies the safety of the intelligent vehicle systems. However, automatic detection and classification of traffic signs by such intelligent vehicle systems is a challenging task due to various factors such as variation in light illumination, different viewpoints, colour faded traffic sign, motion blurring, etc. The deep learning models have proved to provide solutions to overcome these factors. This paper proposed deep learning-based residual network for traffic sign detection and classification (DLRN-TSDC) model for effective Indian Traffic Sign Board Recognition. The DLRN-TSDC model makes use of Colour space threshold segmentation technique for the effective identification of sign boards. Simultaneously, pre-processing of the detected traffic sign takes place in three distinct ways such as clipping of edges, image enhancement and size normalization. In addition, the ResNet-50 model is used as a feature extractor and a classifier to determine the final class label of the traffic sign board. Extensive experimental analysis was carried out to validate the effective performance of the DLRN-TSDC model and for the precision, recall, Intersection over Union (IoU) and accuracy scores are 98.76%, 98.92%, 89.56% and 98.84%, respectively.
#معرفی_مقاله #یادگیری_عمیق #object_detection
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
A Deep Learning-Based Residual Network Model for Traffic Sign Detection and Classification
Traffic sign board recognition is a very significant work for the upcoming driver assistance intelligent vehicle systems. The ability to detect such traffic signs from the real road scenes intensifies the safety of the intelligent vehicle systems. However, automatic detection and classification of traffic signs by such intelligent vehicle systems is a challenging task due to various factors such as variation in light illumination, different viewpoints, colour faded traffic sign, motion blurring, etc. The deep learning models have proved to provide solutions to overcome these factors. This paper proposed deep learning-based residual network for traffic sign detection and classification (DLRN-TSDC) model for effective Indian Traffic Sign Board Recognition. The DLRN-TSDC model makes use of Colour space threshold segmentation technique for the effective identification of sign boards. Simultaneously, pre-processing of the detected traffic sign takes place in three distinct ways such as clipping of edges, image enhancement and size normalization. In addition, the ResNet-50 model is used as a feature extractor and a classifier to determine the final class label of the traffic sign board. Extensive experimental analysis was carried out to validate the effective performance of the DLRN-TSDC model and for the precision, recall, Intersection over Union (IoU) and accuracy scores are 98.76%, 98.92%, 89.56% and 98.84%, respectively.
#معرفی_مقاله #یادگیری_عمیق #object_detection
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
SpringerLink
A Deep Learning-Based Residual Network Model for Traffic Sign Detectio
Traffic sign board recognition is a very significant work for the upcoming driver assistance intelligent vehicle systems. The ability to detect such traffic signs from the real road scenes...
همانطور که قبلا اشاره کرده بودیم کاربردهای یادگیری عمیق در حوزه شبکه و IOT در حال افزایش است. در مقاله ای که چند روز پیش ارایه شد، از ایده شبکه کپسول در کنار LSTM استفاده شده است.
Caps-LSTM: A Novel Hierarchical Encrypted VPN Network Traffic Identification Using CapsNet and LSTM
At present, encryption technologies are widely applied in the network, providing a lot of opportunities for attackers to hide their command and control activities, and thus encrypted traffic detection technology is one of the important means to prevent malicious attacks in advance. The existing methods based on machine learning cannot get rid of the artificial dependence of feature selection. Moreover, deep learning methods ignore the hierarchical characteristics of traffic. Therefore, we propose a novel deep neural network that combines CapsNet and LSTM to implement a hierarchical encrypted traffic recognition model, Caps-LSTM, which splits the traffic twice and classifies the encrypted traffic hierarchically based on the temporal and spatial characteristics, where CapsNet learns the lower spatial characteristics of the traffic and LSTM learns the upper temporal characteristics of the traffic. Finally, the softmax classifier is used to achieve effective detection of encrypted traffic services and specific application categories. Compared with the existing advanced methods based on the common data set ISCX VPN-nonVPN, the experimental results show that Caps-LSTM is more effective.
#معرفی_مقاله #IOT #یادگیری_عمیق #capsule_network #شبکه_عصبی #LSTM
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Caps-LSTM: A Novel Hierarchical Encrypted VPN Network Traffic Identification Using CapsNet and LSTM
At present, encryption technologies are widely applied in the network, providing a lot of opportunities for attackers to hide their command and control activities, and thus encrypted traffic detection technology is one of the important means to prevent malicious attacks in advance. The existing methods based on machine learning cannot get rid of the artificial dependence of feature selection. Moreover, deep learning methods ignore the hierarchical characteristics of traffic. Therefore, we propose a novel deep neural network that combines CapsNet and LSTM to implement a hierarchical encrypted traffic recognition model, Caps-LSTM, which splits the traffic twice and classifies the encrypted traffic hierarchically based on the temporal and spatial characteristics, where CapsNet learns the lower spatial characteristics of the traffic and LSTM learns the upper temporal characteristics of the traffic. Finally, the softmax classifier is used to achieve effective detection of encrypted traffic services and specific application categories. Compared with the existing advanced methods based on the common data set ISCX VPN-nonVPN, the experimental results show that Caps-LSTM is more effective.
#معرفی_مقاله #IOT #یادگیری_عمیق #capsule_network #شبکه_عصبی #LSTM
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
SpringerLink
Caps-LSTM: A Novel Hierarchical Encrypted VPN Network Traffic Identifi
At present, encryption technologies are widely applied in the network, providing a lot of opportunities for attackers to hide their command and control activities, and thus encrypted traffic detection technology is one of the important means to prevent malicious...
یکی از نیازهای افرادی که در حوزه های مربوط به computer vision و تصمیم گیری در یادگیری عمیق کار می کنند، شبیه سازی است. در ادامه می خواهیم agent های موجود در موتور Unity را معرفی کنیم.
Machine Learning Agents
لینک Github پیاده سازیها
#معرفی_منبع #معرفی_منبع_آموزشی #یادگیری_عمیق #یادگیری_ماشین #کتابخانه #unity #یادگیری_عمیق_تقویتی
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Machine Learning Agents
لینک Github پیاده سازیها
#معرفی_منبع #معرفی_منبع_آموزشی #یادگیری_عمیق #یادگیری_ماشین #کتابخانه #unity #یادگیری_عمیق_تقویتی
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
یکی از مقالات تاثیرگذار تاریخ هوش مصنوعی در سال 2015 چاپ شد. مقاله ای که در Nature به چاپ رسید و سبب شد بیش از پیش امیدها به یادگیری تقویتی عمیق افزایش پیدا کند. در ادامه لینک مقاله Human-level control through deep reinforcement learning را قرار می دهیم.
https://www.datascienceassn.org/sites/default/files/Human-level%20Control%20Through%20Deep%20Reinforcement%20Learning.pdf
ایده اولیه این کار در سال 2005 در مقاله Neural Fitted Iteration مطرح شده بود ولی در سال 2015 روشی ارایه شد تا یادگیری، پایدار شود.
پیشنهاد میشود تعداد citation مقاله سال 2015 را ببینید تا از اهمیت این مقاله با خبر شوید.
#یادگیری_عمیق #یادگیری_ماشین #معرفی_مقاله #یادگیری_تقویتی_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
https://www.datascienceassn.org/sites/default/files/Human-level%20Control%20Through%20Deep%20Reinforcement%20Learning.pdf
ایده اولیه این کار در سال 2005 در مقاله Neural Fitted Iteration مطرح شده بود ولی در سال 2015 روشی ارایه شد تا یادگیری، پایدار شود.
پیشنهاد میشود تعداد citation مقاله سال 2015 را ببینید تا از اهمیت این مقاله با خبر شوید.
#یادگیری_عمیق #یادگیری_ماشین #معرفی_مقاله #یادگیری_تقویتی_عمیق
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
یکی از نیازها در زمینه های یادگیری، دیتاست است. در مقاله مروری که اخیرا ارایه شده، راه های افزایش دیتا برای NLP مرور شده اند. اگر در زمینه NLP و یادگیری عمیق کار می کنید، این مقاله می تواند کمکتان کند. ما نیز خواندن مقاله را پیشنهاد می کنیم. حتما فهرست مطالب مقاله را ببینید.
As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods in detail according to the above categories. Further, we also introduce their applications in NLP tasks as well as the challenges.
لینک مقاله Data Augmentation Approaches in Natural Language Processing: A Survey
#یادگیری_عمیق #پردازش_زبان_طبیعی #NLP #دیتاست #data_augmentation #مقاله_مروری
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods in detail according to the above categories. Further, we also introduce their applications in NLP tasks as well as the challenges.
لینک مقاله Data Augmentation Approaches in Natural Language Processing: A Survey
#یادگیری_عمیق #پردازش_زبان_طبیعی #NLP #دیتاست #data_augmentation #مقاله_مروری
🌴 سایت | 🌺 کانال | 🌳 پشتیبانی
Telegram
Bias Variance
🌴 سایت:
https://biasvariance.net
🌺 کانال تلگرام:
@biasvariance_ir
🌳 پشتیبانی:
@biasvariance
🌷 اینستاگرام:
https://www.instagram.com/bvariance/
https://biasvariance.net
🌺 کانال تلگرام:
@biasvariance_ir
🌳 پشتیبانی:
@biasvariance
🌷 اینستاگرام:
https://www.instagram.com/bvariance/