检索结果-内蒙古大学图书馆

Efficient Skip Connections Realization for Secure Inference on Encrypted Data 1

7th International Symposium on Cyber Security, Cryptology, and Machine Learning, CSCML 2023

作者： Drucker, Nir Zimerman, Itamar IBM Research Haifa Israel

ISBN: (数字)9783031346712

ISBN: (纸本)9783031346705

Homomorphic Encryption (HE) is a cryptographic tool that allows performing computation under encryption, which is used by many privacy-preserving machine learning solutions, for example, to perform secure classification. Modern deep learning applications yield good performance for example in image processing tasks benchmarks by including many skip connections. The latter appears to be very costly when attempting to execute model inference under HE. In this paper, we show that by replacing (mid-term) skip connections with (short-term) Dirac parameterization and (long-term) shared-source skip connection we were able to reduce the skip connections burden for HE-based solutions, achieving × 1.3 computing power improvement for the sameaccuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification 36

NodeFormer: A Scalable Graph Structure Learning Transformer ...

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Wu, Qitian Zhao, Wentao Li, Zenan Wipf, David Yan, Junchi Shanghai Jiao Tong Univ Dept Comp Sci & Engn Shanghai Peoples R China Amazon Web Serv Shanghai AI Lab Shanghai Peoples R China SJTU MoE Key Lab Artificial Intelligence Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China

ISBN: (纸本)9781713871088

Graph neural networks have been extensively studied for learning with inter-connected data. Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing, heterophily, handling long-range dependencies, edge incompleteness and particularly, the absence of graphs altogether. While a plausible solution is to learn new adaptive topology for message passing, issues concerning quadratic complexity hinder simultaneous guarantees for scalability and precision in large networks. In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as NODEFORMER. Specifically, the efficient computation is enabled by a kernerlized Gumbel-Softmax operator that reduces the algorithmic complexity to linearity w.r.t. node numbers for learning latent graph structures from large, potentially fully-connected graphs in a differentiable manner. We also provide accompanying theory as justification for our design. Extensive experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs (with up to 2M nodes) and graph-enhanced applications (e.g., image classification) where input graphs are missing. The codes are available at https://***/qitianwu/NodeFormer.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT SELF-CALIBRATED CONVOLUTION FOR REAL-TIME image SUPER-RESOLUTION 29

EFFICIENT SELF-CALIBRATED CONVOLUTION FOR REAL-TIME IMAGE SU...

引用

IEEE International Conference on image processing (ICIP)

作者： Hamida, Adnan Alfarraj, Motaz Zummo, Salam A. King Fahd Univ Petr & Minerals Elect Engn Dept Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals SDAIA KFUPM Joint Res Ctr Artificial Intelligence Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals Ctr Commun & Sensing Dhahran 31261 Saudi Arabia

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

With the recent advancements in Convolutional neural Network (CNN) architectures designs, many image processing tasks benefited from the design of such deep and complex networks including image super-resolution (SR). While deep and complex models achieve improved SR reconstruction, they lack the practicality in implementation for real-time applications, such as in mobile phones or online conferencing. This is due to the large number of parameters and excessive required multiply-accumulate operations (MACs). In this paper, an accurate real-time SR model structure is proposed. The proposed structure reduces the required number of MACs by performing all operations on low dimensional feature maps and reduces the model parameters by utilizing depthwise separable convolutional (DSC) layers. An efficient version of the recently introduced self-calibrated convolution with pixel attention (SC-PA) is introduced to further improve feature representation. Experimental results show that the proposed model improves performance in objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) index, over similar complexity real-time SR models.

关键词： real-time image super-resolution depth-wise separable convolution self-calibrated convolution pixel attention image quality assessment

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Investigation for Attacks on artificial Intelligence 1

Digital Forensics Investigation for Attacks on Artificial In...

引用

1st International Conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Manasa, Sanyasi Kumar, Kukatlapalli Pradeep Bengaluru India

ISBN: (纸本)9781607685395

The new research approaches are needed to be adopted to deal with security threats in AI based systems. This research is aimed at investigating the artificial Intelligence (AI) attacks that are "malicious by design". It also deals with conceptualization of the problem and strategies for attacks on artificial Intelligence (AI) using Digital Forensic tools. A specific class of problems in Adversarial attacks are tampering of images for computational processing in applications of Digital Photography, Computer Vision, Pattern Recognition (Facial Mapping algorithms). State-of-the-art developments in forensics such as 1. Application of end-to-end neural Network Training pipeline for image rendering and provenance analysis, 2. Deep-fake image analysis using frequency methods, wavelet analysis & tools like - Amped Authenticate, 3. Capsule networks for detecting forged images 4. Information transformation for Feature extraction via image Forensic tools such as EXIF-SC, Splice Radar, Noiseprint 5. Application of generative adversarial networks (GAN) based models as anti-image Forensics [8], will be studied in great detail and a new research approach will be designed incorporating these advancements for utility of Digital Forensics. © The Electrochemical Society

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Retinex by Autoencoders 16

Retinex by Autoencoders

引用

16th International Conference on Signal-image Technology and Internet-Based Systems (SITIS)

作者： Pezzoni, Claudio Mio, Corrado Barsotti, Annalisa Univ Milan Dipartimento Informat Giovanni degli Antoni Via Celoria 18 I-20133 Milan Italy Khalifa Univ Sci & Technol EBTIC Abu Dhabi City U Arab Emirates Univ Milan Dipartimento Informat I-20133 Milan Italy

ISBN: (纸本)9781665464956

The Retinex algorithms find wide applications as image enhancers, for their capability of preserving edges, while at the same time attenuating smooth gradients and chromatic dominants. They are characterized by the fact that the output chromatic intensity of a pixel is not determined in isolation (or looking only at the contiguous pixels) but through an operation of comparison to different local and remote areas of the image. This local/global comparison implies also a high computational cost for the algorithms: their complexity is not linear with the number of pixels;furthermore, the more systematic the comparison, the higher the complexity. Thus, most Retinex algorithms are unfit for real-time processing. The recent development of efficient Machine Learning architectures for image processing has raised the question of whether one of the Retinex "transforms" could be efficiently learned by training a feed-forward artificial neural Network, thus creating a model characterized by short processing time. Selecting a variant of the Random Spray Retinex model - FuzzyRSR - as representative of the Retinex family, and choosing suitably structured autoencoder neural networks, we found that we could accurately reproduce the Retinex effects. The computational cost of the training phase was moderate, while that of the inference phases was linear in the number of pixels, and three orders of magnitude lower than the one of FuzzyRSR, thus making the ANN implementation of Retinex suitable for real-time processing.

关键词： Autoencoders FuzzyRSR image Enhancement Random Spray Retinex Retinex

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Lightweight CNN Acceleration System for Real-Time Recognition

FPGA-Based Lightweight CNN Acceleration System for Real-Time...

引用

International Conference on Integrated Circuits and Microsystems (ICICM)

作者： Junlei Ju Cheng Liu School of Microelectronics Shanghai University Shanghai China

ISBN: (数字)9798331509453

ISBN: (纸本)9798331520243

In recent years, convolutional neural networks (CNNs) have become the core of many artificial intelligence applications, especially in fields such as image recognition and speech recognition. Deploying convolutional neural networks in hardware, as opposed to software, can increase speed and reduce power consumption. In this article, we propose an FPGA-based convolutional neural network acceleration system. This system optimizes LeNet-5 into a lightweight convolutional neural network model by replacing traditional convolution with depthwise separable convolutions and reducing the number of fully connected layers. After designing a parallel processing scheme for the computation process of the model, a CNN acceleration IP core is implemented using Verilog and applied to real-time handwritten digit recognition. This system can recognize one frame of image in 326.24µs, which is approximately 1s faster than CPU recognition. The total power consumption of the entire system is 1.947W, meeting the requirements of high real-time performance and low power consumption.

关键词： Handwriting recognition Power demand image recognition Convolution Computational modeling Speech recognition Real-time systems Central processing Unit Convolutional neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural networks for the classification of chest X-rays in the IoT era

引用

MULTIMEDIA TOOLS AND applications 2021年第19期80卷 29051-29065页

作者： Almezhghwi, Khaled Serte, Sertan Al-Turjman, Fadi Coll Elect Technol Elect & Elect Engn Tripoli Libya Near East Univ Elect & Elect Engn Via Mersin 10 Nicosia North Cyprus Turkey Near East Univ Dept Artificial Intelligence Via Mersin 10 Nicosia North Cyprus Turkey Near East Univ Res Ctr AI & IoT Via Mersin 10 Nicosia North Cyprus Turkey

Chest X-ray medical imaging technology allows the diagnosis of many lung diseases. It is known that this technology is frequently used in hospitals, and it is the most accurate way of detecting most thorax diseases. Radiologists examine these images to identify lung diseases;however, this process can require some time. In contrast, an automated artificial intelligence system could help radiologists detect lung diseases more accurately and faster. Therefore, we propose two artificial intelligence approaches for processing and identifying chest X-ray images to detect chest diseases from such images. We introduce two novel deep learning methods for fast and automated classification of chest X-ray images. First, we propose the use of support vector machines based on the AlexNet model. Second, we develop support vector machines based on the VGGNet16 method. Combined deep networks with a robust classifier have shown that the proposed methods outperform AlexNet and VGG16 deep learning approaches for the chest X-ray image classification tasks. The proposed AlexNet and VGGNet based SVM provide average area under the curve values of 98% and 97%, respectively, for twelve chest X-ray diseases.

关键词： Convolutional neural networks Deep learning

来源：评论

学校读者我要写书评

暂无评论

Age and Sex Estimation in Children and Young Adults Using Panoramic Radiographs with Convolutional neural networks

引用

APPLIED SCIENCES-BASEL 2024年第16期14卷 7014页

作者： Sahin, Tugce Nur Kolus, Turkay Karamanoglu Mehmetbey Univ Ahmet Kelesoglu Fac Dent Dept Pedodont TR-70200 Karaman Turkiye Karamanoglu Mehmetbey Univ Ahmet Kelezoglu Fac Dent Dept Restorat Dent TR-70200 Karaman Turkiye

image processing with artificial intelligence has shown significant promise in various medical imaging applications. The present study aims to evaluate the performance of 16 different convolutional neural networks (CNNs) in predicting age and gender from panoramic radiographs in children and young adults. The networks tested included DarkNet-19, DarkNet-53, Inception-ResNet-v2, VGG-19, DenseNet-201, ResNet-50, GoogLeNet, VGG-16, SqueezeNet, ResNet-101, ResNet-18, ShuffleNet, MobileNet-v2, NasNet-Mobile, AlexNet, and Xception. These networks were trained on a dataset of 7336 radiographs from individuals aged between 5 and 21. Age and gender estimation accuracy and mean absolute age prediction errors were evaluated on 340 radiographs. Statistical analyses were conducted using Shapiro-Wilk, one-way ANOVA, and Tukey tests (p < 0.05). The gender prediction accuracy and the mean absolute age prediction error were, respectively, 87.94% and 0.582 for DarkNet-53, 86.18% and 0.427 for DarkNet-19, 84.71% and 0.703 for GoogLeNet, 81.76% and 0.756 for DenseNet-201, 81.76% and 1.115 for ResNet-18, 80.88% and 0.650 for VGG-19, 79.41% and 0.988 for SqueezeNet, 79.12% and 0.682 for Inception-Resnet-v2, 78.24% and 0.747 for ResNet-50, 77.35% and 1.047 for VGG-16, 76.47% and 1.109 for Xception, 75.88% and 0.977 for ResNet-101, 73.24% and 0.894 for ShuffleNet, 72.35% and 1.206 for AlexNet, 71.18% and 1.094 for NasNet-Mobile, and 62.94% and 1.327 for MobileNet-v2. No statistical difference in age prediction performance was found between DarkNet-19 and DarkNet-53, which demonstrated the most successful age estimation results. Despite these promising results, all tested CNNs performed below 90% accuracy and were not deemed suitable for clinical use. Future studies should continue with more-advanced networks and larger datasets.

关键词： age determination by teeth artificial intelligence dental age neural network models panoramic radiography

来源：评论

学校读者我要写书评

暂无评论

TODOS: Thermal sensOr Data-driven Occupancy Estimation System for Smart Buildings 23

TODOS: Thermal sensOr Data-driven Occupancy Estimation Syste...

引用

10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys)

作者： Rajabi, Hamid Ding, Xianzhong Du, Wan Cerpa, Alberto Univ Calif Merced Merced CA 95343 USA

ISBN: (纸本)9798400702303

Occupancy sensing and estimation in large commercial buildings has become a significant problem to be solved, with applications ranging from occupancy-based HVAC control to space planning, and security, etc. Thermal sensing is a promising technology to solve this problem, being easy to deploy in practice and allowing an actual occupancy count in a particular room without violating the data and privacy concerns. While initial strides have been made to solve this problem with thermal arrays, there are many problems that remain unsolved, including accuracy performance, overlapping of sensing areas that lead to under/over-counting, and data training requirements for different zones. In this paper, we introduce TODOS1, a novel system for estimating occupancy in intelligent buildings. TODOS uses a low-cost, low-power thermal sensor array along with a passive infrared sensor. We introduce a novel data processing pipeline that allows us to automatically extract features from the thermal images using an artificial neural network. Through an extensive experimental evaluation(2), we show that TODOS provides occupancy detection accuracy of 98% to 100% under different scenarios. In addition, it solves the issue of occupancy over/under-counting by overlapping sensing areas when using multiple thermal sensors in large rooms. This is done by treating the entire area as a single input thermal image instead of partitioning the area into multiple thermal images individually processed. Furthermore, TODOS introduces a data augmentation technique that allows the generation of training data for rooms of different sizes and shapes, without requiring specific training data from each room. Using these data, TODOS can train specifically designed neural networks optimized for any room size and shape, and achieve almost the same level of occupancy detection accuracy in rooms where experimental labeled training data is available, making it a viable solution that generalizes to the different room

关键词： smart buildings occupancy estimation HVAC systems thermal occupancy sensor neural networks data augmentation

来源：评论

学校读者我要写书评

暂无评论

From one-dimensional to multidimensional map neural networks

引用

APPLIED SOFT COMPUTING 2024年 167卷

作者： Vaghefi, Sayed Yousef Monir Safi-Esfahani, Faramarz Fekri-Ershad, Shervan Vaghefi, Sayed Mahmoud Monir Islamic Azad Univ Fac Comp Engn Najafabad Branch Najafabad Iran Islamic Azad Univ Big Data Res Ctr Najafabad Branch Najafabad Iran Isfahan Univ Technol IUT Dept Mat Engn Esfahan Iran

In the contemporary landscape, artificial neural networks transcend their traditional role of function approximation and have found diverse applications in fields such as image classification, machine translation, speech recognition, and natural language processing. In some datasets, traditional architectures exhibit low test and training accuracy, coupled with high loss and prolonged training times. This study aims to introduce innovative neural network architectures that outperform conventional models. The research presents a novel framework integrating one-dimensional and multidimensional map neural networks, consisting of three distinct architectures: 1D-Map, 2D-Map, and 3D-Map. A systematic performance comparison with traditional models is conducted following the implementation of these architectures. The evaluation spans four datasets, encompassing the domains of heat treatment of electroless Ni-P nano coatings, letter recognition, combined cycle power plants, and Seoul bike sharing demand. In the heat treatment dataset, the proposed 3D-Map architecture reached 0.055 higher average test accuracy than traditional MLP architecture. In the letter recognition dataset, the test accuracy of 3D-Map architecture was 0.0523 higher than the test accuracy of the LSTM architecture. In the combined cycle power plant dataset, the test accuracy of the 3D-Map architecture was 0.0612 more than the test accuracy of the MLP architecture. In the Seoul bike-sharing demand dataset, the test accuracy of the 2D-Map architecture was 0.0696 higher than the test accuracy of the LSTM architecture. The study's findings underscore the consistently superior performance of the proposed architectures compared to their traditional counterparts.

关键词： One-dimensional and multidimensional map neural networks 1D-Map neural network 2D-Map neural network 3D-Map neural network neural network modeling

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：