检索结果-内蒙古大学图书馆

3rd International conference on Computational Electronics for Wireless Communications, ICCWC 2023

作者： Ingale, Sumedh Bamnote, G.R. Prof. Ram Meghe Institute of Technology & Research Badnera Amravati India

ISBN: (纸本)9789819719457

The process that produces written descriptions that effectively represent the meaning and context of an image is known as image captioning. To integrate visual and textual data, it needs to blend computer vision and natural language processing methods. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs), such as long-short-term memory (LSTM) networks, are two methods used for captioning images. High-level visual features from the input image are extracted by the CNN, and the RNN uses those features to generate the matching captions. Residual Network is a deep CNN architecture with exceptional results in a range of computer vision tasks, including the classification of images. ResNet has been used as the foundation for extracting picture features. ResNet and CNN abstracts an image's visual information via feature extraction and uses neural networks with recurrent architecture to provide meaningful, contextually appropriate captions. Machines are now able to comprehend and speak about the visual world in a manner similar to humans because of the integration of computer vision and natural language processing. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis Of Traffic Sign Recognition Using artificial neural Network Algorithm Compared With Accuracy Of Recurrent neural networks 9

Analysis Of Traffic Sign Recognition Using Artificial Neural...

引用

9th International conference on Applying New Technology in Green Buildings, ATiGB 2024

作者： Amos, P. Narendran, S. Keerthivasan, M. Institute of Electronics and Communication Engineering Saveetha School of Engineering Simats Department of Nanotechnology Chennai India Institute of Electronics and Communication Engineering Saveetha School of Engineering Simats Chennai India

ISBN: (纸本)9798331505042

The purpose of this work is to improve Traffic sign recognition using machine learning to improve comprehension of traffic signs. The Novel artificial neural Network (ANN) method is compared with Recurrent neural Network (RNN) to find accuracy. Symbols on the traffic sign boards are used as an image processing input picture. Novel artificial neural Network (ANN) (Group 1) has ten samples and Recurrent neural Network (RNN) (Group 2) has ten samples and in total 146 samples. With the help of image analysis, a Novel artificial neural Network (ANN) and Recurrent neural Network (RNN) are used to predict the accuracy of traffic sign recognition. The training and testing splits are varied for each network type. The G Power test used is about 85% with *** the process is done for αa=0.05 and N=0.85 iterations. Novel artificial neural Network (ANN) (90.585 %) has the increased accuracy over Recurrent neural Network (RNN) (76.649%) with a statistical significance value of 0.042 (p © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Operator-Learning-Inspired Modeling of neural Ordinary Differential Equations 38

Operator-Learning-Inspired Modeling of Neural Ordinary Diffe...

引用

38th AAAI conference on artificial Intelligence (AAAI) / 36th conference on Innovative applications of artificial Intelligence / 14th Symposium on Educational Advances in artificial Intelligence

作者： Cho, Woojin Cho, Seunghyeon Jin, Hyundong Jeon, Jinsung Lee, Kookjin Hong, Sanghyun Lee, Dongeun Choi, Jonghyun Park, Noseong Yonsei Univ Seoul South Korea Arizona State Univ Tempe AZ USA Oregon State Univ Corvallis OR USA Texas A&M Univ Commerce College Stn TX USA

ISBN: (纸本)1577358872

neural ordinary differential equations (NODEs), one of the most influential works of the differential equation-based deep learning, are to continuously generalize residual networks and opened a new field. They are currently utilized for various downstream tasks, e.g., image classification, time series classification, image generation, etc. Its key part is how to model the time-derivative of the hidden state, denoted dh(t)/dt. People have habitually used conventional neural network architectures, e.g., fully-connected layers followed by non-linear activations. In this paper, however, we present a neural operator-based method to define the time-derivative term. neural operators were initially proposed to model the differential operator of partial differential equations (PDEs). Since the time-derivative of NODEs can be understood as a special type of the differential operator, our proposed method, called branched Fourier neural operator (BFNO), makes sense. In our experiments with general downstream tasks, our method significantly outperforms existing methods.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A survey of the vision transformers and their CNN-transformer based variants

引用

artificial INTELLIGENCE REVIEW 2023年第SUPPL3期56卷 S2917-S2970页

作者： Khan, Asifullah Raufu, Zunaira Sohail, Anabia Khan, Abdul Rehman Asif, Hifsa Asif, Aqsa Farooq, Umair Pakistan Inst Engn & Appl Sci Dept Comp & Informat Sci Pattern Recognit Lab Islamabad 45650 Pakistan Pakistan Inst Engn & Appl Sci PIEAS Artificial Intelligence Ctr PAIC Islamabad 45650 Pakistan Pakistan Inst Engn & Appl Sci Ctr Math Sci Islamabad 45650 Pakistan Khalifa Univ Sci & Technol Dept Elect Engn & Comp Sci Abu Dhabi U Arab Emirates Air Univ E-9 Islamabad 44230 Pakistan

Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationships in images, offer large learning capacity. However, they may suffer from limited generalization as they do not tend to model local correlation in images. Recently, in vision transformers hybridization of both the convolution operation and self-attention mechanism has emerged, to exploit both the local and global image representations. These hybrid vision transformers, also referred to as CNN-Transformer architectures, have demonstrated remarkable results in vision applications. Given the rapidly growing number of hybrid vision transformers, it has become necessary to provide a taxonomy and explanation of these hybrid architectures. This survey presents a taxonomy of the recent vision transformer architectures and more specifically that of the hybrid vision transformers. Additionally, the key features of these architectures such as the attention mechanisms, positional embeddings, multi-scale processing, and convolution are also discussed. In contrast to the previous survey papers that are primarily focused on individual vision transformer architectures or CNNs, this survey uniquely emphasizes the emerging trend of hybrid vision transformers. By showcasing the potential of hybrid vision transformers to deliver exceptional performance across a range of computer vision tasks, this survey sheds light on the future directions of this rapidly evolving architecture.

关键词： Auto encoder Channel boosting Computer vision Convolutional neural networks Deep learning Hybrid vision transformers image processing Self-attention Transformer

来源：评论

学校读者我要写书评

暂无评论

Design Space Exploration of CNN Accelerators based on GSA Algorithm

Design Space Exploration of CNN Accelerators based on GSA Al...

引用

9th International conference on Signal and image processing (ICSIP)

作者： Xie, Zheren Dai, Kui Wu, Zhilin Wang, Jinyue Lu, Xin Liu, Shuanglong Hunan Normal Univ Key Lab Low Dimens Quantum Struct & Quantum Contr Key Lab Phys & Devices Postmoore Era Coll Hunan Prov Changsha Peoples R China

ISBN: (纸本)9798350350920

Convolutional neural networks (CNNs) exhibit exceptional performance within the image processing domain. The acceleration of convolutions for CNNs has consistently represented a focal point within machine learning hardware accelerators. However, with the continuous development of CNNs, the design costs and project workloads of hardware accelerators have significantly increased. To enhance accelerator performance while reducing time-related expenses, it is necessary to determine a series of optimal design parameters during the early stages of accelerator design. To achieve this objective, the concept of design space exploration (DSE) for CNN accelerators is proposed. However, as neural networks become increasingly complex, the demands for DSE methods have also grown, rendering the existing methods unsuitable for meeting the real-time requirements of accelerators, and unable to discover the optimal design. In this paper, we introduce a DSE framework based on the Genetic Simulated Annealing (GSA) algorithm. The proposed framework autonomously generates the hardware design parameters such as parallelism degrees based on the resource constraint and CNN model. Our method is evaluated with two typical CNN accelerators. Experimental results show that our method largely improves the DSE efficiency, reducing the exploration time by up to 73.7x when compared to existing DSE methods.

关键词： Convolutional neural networks (CNNs) Design Space Exploration (DSE) Hardware Accelerator Genetic Simulated Annealing (GSA)

来源：评论

学校读者我要写书评

暂无评论

Vector-Valued Hopfield neural networks and Distributed Synapse Based Convolutional and Linear Time-Variant Associative Memories

引用

neural processing LETTERS 2023年第4期55卷 4163-4182页

作者： Garimella, Rama Murthy Valle, Marcos Eduardo Vieira, Guilherme Rayala, Anil Munugoti, Dileep Mahindra Univ Ecole Cent Sch Engn Dept Comp Sci Hyderabad India Univ Estadual Campinas Campinas SP Brazil Int Inst Informat Technol Hyderabad India Indian Inst Technol Gauhati India

The Hopfield network is an example of an artificial neural network used to implement associative memories. A binary digit represents the neuron's state of a traditional Hopfield neural network. Inspired by the human brain's ability to cope simultaneously with multiple sensorial inputs, this paper presents three multi-modal Hopfield-type neural networks that treat multi-dimensional data as a single entity. In the first model, called the vector-valued Hopfield neural network, the neuron's state is a vector of binary digits. Synaptic weights are modeled as finite impulse response (FIR) filters in the second model, yielding the so-called convolutional associative memory. Finally, the synaptic weights are modeled by linear time-varying (LTV) filters in the third model. Besides their potential applications for multi-modal intelligence, the new associative memories may also be used for signal and image processing and solve optimization and classification tasks.

关键词： Vector-valued Hopfield neural network Finite impulse response filter Convolution Sub-sampling matrix Linear time-varying filter Multimodal intelligence

来源：评论

学校读者我要写书评

暂无评论

Bayesian Hierarchical Convolutional neural networks 5

Bayesian Hierarchical Convolutional Neural Networks

引用

conference on artificial Intelligence and Machine Learning for Multi-Domain Operations applications V

作者： Bensen, Alexis Kahana, Adam Woods, Zerotti Johns Hopkins Univ Appl Phys Lab 11100 Johns Hopkins Rd Laurel MD 20723 USA

ISBN: (数字)9781510661936

ISBN: (纸本)9781510661929;9781510661936

The Hierarchical Bayesian Convolutional neural Network (HCNN) is a machine learning algorithm that attempts to use the natural hierarchical structure of data. HCNN has demonstrated gains in robustness, accuracy, and reporting capabilities by addressing the technical challenge of classifying data at different levels of a hierarchical structure. There is a significant operational benefit in classifying at different levels of an ontology where the extracted knowledge is used for future decision-making, especially when classification at the finest level is unfeasible.

关键词： Data modeling Education and training Animal model studies Animals neural networks Performance modeling Convolutional neural networks image classification Classification systems artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Scale-preserving automatic concept extraction (SPACE)

引用

MACHINE LEARNING 2023年第11期112卷 4495-4525页

作者： Posada-Moreno, Andres Felipe Kreiskoether, Lukas Glander, Tassilo Trimpe, Sebastian Rhein Westfal TH Aachen Inst Data Sci Mech Engn DSME Aachen Germany Deevio GmbH Berlin Germany

Convolutional neural networks (CNN) have become a common choice for industrial quality control, as well as other critical applications in the Industry 4.0. When these CNNs behave in ways unexpected to human users or developers, severe consequences can arise, such as economic losses or an increased risk to human life. Concept extraction techniques can be applied to increase the reliability and transparency of CNNs through generating global explanations for trained neural network models. The decisive features of image datasets in quality control often depend on the feature's scale;for example, the size of a hole or an edge. However, existing concept extraction methods do not correctly represent scale, which leads to problems interpreting these models as we show herein. To address this issue, we introduce the Scale-Preserving Automatic Concept Extraction (SPACE) algorithm, as a state-of-the-art alternative concept extraction technique for CNNs, focused on industrial applications. SPACE is specifically designed to overcome the aforementioned problems by avoiding scale changes throughout the concept extraction process. SPACE proposes an approach based on square slices of input images, which are selected and then tiled before being clustered into concepts. Our method provides explanations of the models' decision-making process in the form of human-understandable concepts. We evaluate SPACE on three image classification datasets in the context of industrial quality control. Through experimental results, we illustrate how SPACE outperforms other methods and provides actionable insights on the decision mechanisms of CNNs. Finally, code for the implementation of SPACE is provided.

关键词： Explainable artificial intelligence image processing neural networks Industry

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Underwater image Enhancement using CNN and GAN

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND applications 2023年第6期14卷 742-748页

作者： Menon, Aparna Aarthi, R. Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Engn Coimbatore India

Underwater image-capturing technology has advanced over the years, and varieties of artificial intelligence -based applications have been developed on digital and synthetic images. The low-quality and low-resolution underwater images are challenging factors for use in existing image processing in computer vision applications. Degraded or low-quality photos are common issues in the underwater imaging process due to natural factors like low illumination and scattering. The recent techniques use deep learning architectures like CNN, GAN, or other models for image enhancement. Although adversarial -based architectures provide good perceptual quality, they performed worse in quantitative tests compared with convolutional-based networks. A hybrid technique is proposed in this paper that blends both designs to gain advantages of the CNN and GAN architectures. The generator component produces or makes images, which contributes to the creation of a sizable training set. The EUVP dataset is used for experimentation for model training and testing. The PSNR score was observed to measure the visual quality of the resultant images produced by models. The proposed system was able to provide an improved image with a higher PSNR score and SSIM score with state-of-the-art methods.

关键词： Convolutional neural network (CNN) generative adversarial networks (GAN) enhancing underwater visual perception (EUVP) underwater images image enhancement computer vision artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Single image Dehazing via Multi-Scale Large Kernel Convolutional neural networks

Single Image Dehazing via Multi-Scale Large Kernel Convoluti...

引用

International Joint conference on neural networks (IJCNN)

作者： Li, Minghui Liu, Wei Kang, Zhiguo Huang, Xiaoyu Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Large-kernel convolutional neural networks (CNNs) have recently achieved remarkable performance comparable to Visual Transformers(ViTs) in high-level vision tasks. However, there are two critical drawbacks hindering its widespread applications in image dehazing. 1) Most large-kernel designs focus expanding the kernel size even further to model stronger long-range dependencies, but this approach brings a substantial amount of computational overhead. 2) As the kernel size increases, the network tends to focus more on the shape of the object over its texture, potentially affecting the details of the recovered image. To overcome these issues, we propose an effective multi-scale large separable kernel attention module (MLSKA) that can simultaneously build long-range and local dependencies in a cost-effective manner to facilitate high-quality image reconstruction. Specifically, MLSKA combines an efficient convolutional decomposition design with multi-scale learning, realizing multi-scale receptive fields while significantly reducing the computational cost and parameters of large-kernel convolution. In addition, we introduce a deformable attention feedforward network (DAFN) to aggregate contextual information. In DAFN, a novel deformable attention gate is designed to provide holistic attention to the feed-forward network (FFN), thereby improving its utilization of critical features. Integrating these two designs into a U-shaped backbone, the proposed multi-scale large-kernel network (MLANet) outperforms state-of-the-art methods on several dehazing benchmarks, achieving the best parameter-performance trade-off.

关键词： image Dehazing Convolutional neural networks Large Kernel Attention Mechanism

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：