检索结果-内蒙古大学图书馆

2024 International Conference on Cloud computing, Performance computing, and Deep Learning, CCPCDL 2024

作者： Lou, Zheng Fan, Lei Tao, Weisong Xu, Chao State Grid Jiangsu Electric Power Co. Ltd. Nanjing210024 China Nanjing Yunchan Information Technology Co. Nanjing211100 China School of computer science and technology Nanjing211189 China

ISBN: (纸本)9781510683044

In today's world, convolution neural networks possess tremendous potential and exhibit remarkable recognition rates in computer vision. However, neural network models are often so large that they are not well-suited for mobile devices, making model compression particularly important. Especially in scenarios with limited hardware resources such as the National Grid, model quantification is essential. This paper introduces an INT8 quantization method for convolution neural networks, which transforms the weights and input/output of the convolution neural network into the logarithmic domain through a non-linear formula. This method provides a better representation of the distribution of small values, resulting in less accuracy loss. Meanwhile, model calibration requires only a limited amount of image data, which reduces the time taken for model calibration while ensuring minimal accuracy loss. Experimental results show that our quantization method results in an accuracy loss of less than 1% on ImageNet and CIFAR. © 2024 SPIE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional encoder-decoder networks based on ensemble learning for semantic segmentation of high-resolution aerial imagery

引用

CCF TRANSACTIONS ON HIGH PERFORMANCE computing 2024年第4期6卷 408-424页

作者： Zhu, Huming Liu, Chendi Li, Qiuming Zhang, Lingyun Wang, Libing Li, Sifan Jiao, Licheng Hou, Biao Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710071 Shaanxi Peoples R China AVIC Xian Aeronaut Comp Tech Res Inst Xian Peoples R China China Star Network Applicat Co Ltd Chongqing Peoples R China

Due to the complexity of object information and optical conditions of high-resolution aerial imagery, it is difficult to obtain fine semantic segmentation performance. Although various deep neural network structures have been proposed to improve segmentation accuracy, there is still room for improving accuracy by making full use of multiscale features and integrating these single weak classifiers into a strong classifier. In this paper, we use a reduced SegNet network to realize the end-to-end classification of high-resolution aerial images. In addition, to use multiscale information, we present the R-SegUnet which combines the feature information of each convolution block in the reduced SegNet encoding network with the feature information of the corresponding convolution block in the decoding network. Furthermore, considering that the surface features in high-resolution aerial images are very complex, we investigate a 6to2_Net that converts the six-classification model into six binary-classification models for the recognition effect on small objects. Finally, we ensemble the above three different models to get the segmentation results. Experiment results on ISPRS Potsdam benchmark dataset show that our algorithm is state-of-the-art method. We also analyze the inference performance of our models on a variety of parallel computing devices.

关键词： Aerial imagery Semantic segmentation Encoder-decoder network Ensemble ISPRS FCN

来源：评论

学校读者我要写书评

暂无评论

Quantum mesh neural network model in precise image diagnosing

引用

optical AND QUANTUM ELECTRONICS 2024年第4期56卷 559-559页

作者： Suneel, Sajja Balaram, Allam Begum, M. Amina Umapathy, K. Reddy, Pundru Chandra Shaker Talasila, Vamsidhar Inst Aeronaut Engn Dept CSE Data Sci Hyderabad India MLR Inst Technol Dept Comp Sci & Engn Hyderabad India Chennai Inst Technol Ctr Nonlinear Syst Chennai India SCSVMV Dept ECE Kanchipuram India SR Univ Dept Comp Sci & Artificial Intelligence Warangal India Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram India

This study introduces QMNN, a quantum mesh neural network model incorporating a Quantum neural network Expectation (QNNE) circuit, and evaluates its performance on MNIST and CIFAR-10 datasets. QMNN employs innovative quantum mesh architecture with increased random layers, while the QNNE circuit, inspired by Circuit 15, integrates extra Hadamard gates for enhanced feature extraction. Implemented using PennyLane libraries, the model demonstrates superior accuracy in training and testing on both datasets compared to classical neural networks, emphasizing its effectiveness in image classification. While classic methods like CNNs may achieve higher accuracy, the significance lies in QMNN's ability, along with the QNNE circuit, to improve accuracy without introducing additional optimization parameters. The observed quantum advantage suggests that strong entanglement between qubits may enhance pixel correlations, highlighting the potential of quantum-inspired models in advancing image diagnostics. Conclusively, this study provides a stepping stone for further research into the synergy between quantum computing and neural networks, showcasing the promising role of QMNN in augmenting image classification accuracy. The results indicate notable improvements, with MNIST testing accuracy reaching 92.80% and CIFAR-10 testing accuracy achieving 36.90%, demonstrating the efficacy of the proposed model.

关键词： Quantum neural network Image diagnosing Dataset Image classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Hindi Handwriting Recognition Using neural network 2

Enhancing Hindi Handwriting Recognition Using Neural Network

引用

2nd International Conference on Advanced computing and Communication Technologies, ICACCTech 2024

作者： Yadav, Narinder Gagandeep Kumar, Mayank Yadav, Shivanshu Ronit Megha Chandigarh University Department of Computer science and engineering Punjab India

ISBN: (纸本)9798331519056

With an emphasis on datasets containing the Devanagari script-the writing system used for the Hindi language-this research explores the application of sophisticated neural network techniques to improve the recognition of Hindi handwriting. optical character recognition systems, which are used in automated form processing, historical manuscript digitisation, and educational programs, depend heavily on handwriting recognition. Conventional recognition techniques frequently lack the robustness and accuracy needed to handle intricate scripts like Devanagari. To increase the accuracy of Hindi handwritten text identification, we employ a number of cutting-edge neural network models in this study, including Convolutional neural networks (CNN) and Recurrent neural networks (RNN), which are specially designed for the Devanagari script. Our tests show notable gains over baseline models, highlighting the significance of well-optimized network designs and training protocols. We also explore the implications of these results for practical applications and future directions in the field of Hindi handwriting recognition systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Quantization of neural network for computing Complex Holograms

Quantization of Neural Network for Computing Complex Hologra...

引用

Computational optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress

作者： Endo, Yutaka Oikawa, Minoru Wilkinson, Timothy D. Shimobaba, Tomoyoshi Ito, Tomoyoshi Institute of Science and Engineering Kanazawa University Kakuma-machi Ishikawa Kanazawa920-1192 Japan Science and Technology Unit Natural Sciences Cluster Kochi University 2-5-1 Akebono-cho Kochi780-8520 Japan Electrical Engineering Division Department of Engineering University of Cambridge 9 JJ Thomson Avenue CambridgeCB3 0FA United Kingdom Graduate School of Engineering Chiba University 1-33 Yayoi Inage Chiba263-8522 Japan

This study demonstrates quantizing of a neural network for computing complex holograms to reduce the model size for computationally limited platforms. We evaluate the model size and output hologram quality, comparing ... 详细信息

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Low-Latency Full Precision optical Convolutional neural network Accelerator 5

Low-Latency Full Precision Optical Convolutional Neural Netw...

引用

Conference on AI and optical Data Sciences V

作者： Jahannia, Belal Ye, Jiachi Altaleb, Salem Peserico, Nicola Asadizanjani, Navid Heidari, Elham Sorger, Volker J. Dalir, Hamed Univ Florida Dept Elect & Comp Engn Gainesville FL 32611 USA

ISBN: (纸本)9781510670679;9781510670662

We demonstrate an optical accelerator for convolutional neural networks using photonic tensor cores that achieves both state-of-the-art accuracy competitive with ideal floating point models, and unprecedented acceleration performance exceeding electronics by orders of magnitude. Across convolutional architectures and image datasets, the photonics-based hardware processes advanced inference workloads faster than alternate ASICs or GPUs. Additionally, power consumption and latency metrics are consistently lowered by using integrated optics - enabling real-time throughput while maintaining accuracy. By unlocking massively parallel and high bandwidth optical matrix operations, this approach promises to revolutionize compute-intensive CNN applications spanning medical imaging, scientific computing, autonomous systems and beyond. Fully integrated optical neural network accelerators now bring extraordinary speed, efficiency and scalability, opening new frontiers in artificial intelligence.

关键词： optical CNN accelerator Systolic Array Multiplier Scalability of Photonic Engines

来源：评论

学校读者我要写书评

暂无评论

Analog optical computing for Artificial Intelligence

引用

Engineering 2022年第3期8卷 133-145页

作者： Jiamin Wu Xing Lin Yuchen Guo Junwei Liu Lu Fang Shuming Jiao Qionghai Dai Department of Automation Tsinghua UniversityBeijing 100084China Institute for Brain and Cognitive Science Tsinghua UniversityBeijing 100084China Beijing National Research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China Beijing Innovation Center for Future Chips Tsinghua UniversityBeijing 100084China Department of Electronic Engineering Tsinghua UniversityBeijing 100084China Department of Physics The Hong Kong University of Science and TechnologyHong Kong 999077China Peng Cheng Laboratory Shenzhen 518055China

The rapid development of artificial intelligence(AI)facilitates various applications from all areas but also poses great challenges in its hardware implementation in terms of speed and energy because of the explosive growth of *** computing provides a distinctive perspective to address this bottleneck by harnessing the unique properties of photons including broad bandwidth,low latency,and high energy *** this review,we introduce the latest developments of optical computing for different AI models,including feedforward neural networks,reservoir computing,and spiking neural networks(SNNs).Recent progress in integrated photonic devices,combined with the rise of AI,provides a great opportunity for the renaissance of optical computing in practical *** effort requires multidisciplinary efforts from a broad *** review provides an overview of the state-of-the-art accomplishments in recent years,discusses the availability of current technologies,and points out various remaining challenges in different aspects to push the *** anticipate that the era of large-scale integrated photonics processors will soon arrive for practical AI applications in the form of hybrid optoelectronic frameworks.

关键词： Artificial intelligence optical computing Opto-electronic framework neural network Neuromorphic computing Reservoir computing Photonics processor

来源：评论

学校读者我要写书评

暂无评论

AGBUNet: an enhanced CNN-UNET architecture for the prediction of above ground biomass using deep learning

引用

neural computing and Applications 2025年第5期37卷 3809-3826页

作者： Arumai Shiney, S. Geetha, R. Department of Computer Science and Engineering S.A. Engineering College Chennai India

Accurate prediction of above ground biomass (AGB) is critical for monitoring forest health and carbon cycling. It is crucial for understanding and managing forest ecosystems. In this paper, we propose an enhanced framework combining convolutional neural network (CNN) and UNet, termed AGBUNet, specifically designed for predicting AGB using remote sensing data. The framework consists of separate CNNs for processing each type of image, whose outputs are subsequently fused in a UNet architecture to enhance prediction accuracy. These modifications include customized convolutional layers, advanced preprocessing techniques, and a novel integration of data prompts from separate Sentinel-1 and Sentinel-2 image processing streams. The AGBUNet integrates Sentinel-1 and Sentinel-2 images to leverage complementary information from synthetic aperture radar (SAR) and optical sensors. This study underscores the potential of the AGBUNet model for enhancing biomass estimation from remote sensing data, contributing to better forest management and ecological monitoring. The performance measures obtained are compared with the other models, and the following results are obtained as follows for MSE value of 298.25, RMSE value of 15.27 and MAE value of 12.21, and the values are satisfying compared with earlier benchmarks. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Few shot image recognition based on convolutional neural network feature extraction and metric learning methods 4

Few shot image recognition based on convolutional neural net...

引用

4th International Conference on Advanced Algorithms and neural networks, AANN 2024

作者： Li, Caihong Blancaflor, Eric B. Mapúa University Manila1002 Philippines School of Electronic Information Engineering Xi'an Siyuan University Shaanxi Xi'an710038 China

ISBN: (纸本)9781510686106

The development of Deep Learning technology has led to a qualitative leap in image recognition. However, the large-scale annotation of data and high-performance computing requirements limit the application of image recognition methods in practical tasks. The research on few shot image recognition emerged as a result. This article mainly discusses the metric learning methods and three network models based on convolutional neural networks, elaborating on their model structures and algorithm ideas. The performance of few shot image recognition under different network models was compared and analyzed through experiments on different datasets. The summary section provides prospects for future research. © 2024 SPIE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-channel Capsule network for Micro-expression Recognition with Multiscale Fusion

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第31期83卷 76833页

作者： Xie, Zhihua Fan, Jiawei Cheng, Shijia Jiangxi Sci & Technol Normal Univ Key Lab Opt Elect & Commun Nanchang Peoples R China

Facial micro-expression (ME), consisting of uncontrollable muscle movements in faces, is an important clue for revealing real people's feelings. Due to the short duration and low intensity, the salient feature representation learning is the main challenge for robust facial ME recognition. To acquire the diverse and spatial relation representation, this paper proposes a simple and yet distinctive micro-expression recognition model based on multiscale convolutional fusion and multi-channel capsule network (MCFMCN). Firstly, the apex frame in a ME clip, located by computing the pixel difference between frames, is filtered by the optical flow transformation. Secondly, a multiscale fusion module is introduced to capture diverse ME related details. Then, to further explore the subtle spatial relations between parts in the ME faces, the multi-channel capsule network is designed to improve the feature representation performance of the traditional single channel capsule network. Finally, the entire ME recognition model is trained and verified on three benchmarks (CASMEII, SAMM, and SMIC) using the associated standard evaluation protocols: unweighted average recall rate (UAR) and unweighted F1 score (UF1). ME recognition experiments indicate that our method based on MCFMCN can improve the UAR (from 75.79% to 83.58%) and UF1(from79.37% to 87.06%) in comparison with the traditional capsule network. Extensive experimental results show the performance of proposed ME recognition is superior to that of works based on pervious single channel capsule network or other state-of-the-art CNN models, which validates the finding that combination of multi-scale analysis and multi-channel capsule network is feasible and effective to improve the ME recognition performance.

关键词： Multiscale fusion Micro-expression recognition Multi-channel capsule network Convolutional neural network optical flow

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：