检索结果-内蒙古大学图书馆

Demystifying Deep Learning: An Introduction to the Mathematics of neural networks 1st

2023年

作者： Douglas J. Santry

ISBN: (数字)9781394205639

ISBN: (纸本)9781394205608

DEMYSTIFYING DEEP LEARNING Discover how to train Deep Learning models by learning how to build real Deep Learning software libraries and verification software! The study of Deep Learning and artificial neural networks (ANN) is a significant subfield of artificial intelligence (AI) that can be found within numerous fields: medicine, law, financial services, and science, for example. Just as the robot revolution threatened blue-collar jobs in the 1970s, so now the AI revolution promises a new era of productivity for white collar jobs. Important tasks have begun being taken over by ANNs, from disease detection and prevention, to reading and supporting legal contracts, to understanding experimental data, model protein folding, and hurricane modeling. AI is everywhere—on the news, in think tanks, and occupies government policy makers all over the world —and ANNs often provide the backbone for AI. Relying on an informal and succinct approach, Demystifying Deep Learning is a useful tool to learn the necessary steps to implement ANN algorithms by using both a software library applying neural network training and verification software. The volume offers explanations of how real ANNs work, and includes 6 practical examples that demonstrate in real code how to build ANNs and the datasets they need in their implementation, available in open-source to ensure practical usage. This approachable book follows ANN techniques that are used every day as they adapt to natural language processing, image recognition, problem solving, and generative applications. This volume is an important introduction to the field, equipping the reader for more advanced study. Demystifying Deep Learning readers will also find: A volume that emphasizes the importance of classification Discussion of why ANN libraries, such as Tensor Flow and Pytorch, are written in C++ rather than Python Each chapter concludes with a “Projects” page to promote students experimenting with real code A supporting library of s

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model Based on CNN Using Keras and TensorFlow to Determine Real-Time Melting Point of Chemical Substances 4th

A Deep Learning Model Based on CNN Using Keras and TensorFlo...

引用

4th International Conference on Machine Intelligence and Signal processing, MISP 2022

作者： Shrivastava, Anurag Sushil, Rama School of Computing DITU Dehradun India

ISBN: (纸本)9789819900848

Deep learning is a subset of machine learning that uses artificial neural networks inspired by human cognitive systems. In many applications, deep learning becomes most successful approach where machine learning has been successful at certain rates. In the succession of these, the proposed deep learning model is suitable for melting-point detection apparatus which determines melting point of chemical substances this apparatus generally used in pharmaceutical and chemical industries. Proposed deep learning model classifies images of chemical’s state (solid or liquid) by deep neural network (DNN), and it consists of TensorFlow framework, libraries like Keras and activation function like ReLu, sigmoid, maxpool and flatten to determine melting point of chemical substances. The proposed model enables to TensorFlow architecture, which can determine the melting point of chemicals in real time on a single board computer. The input image data mainly focuses on chemical’s state, and there are two categories of chemical’s state either solid or liquid. The results discussed in terms of the image classification accuracy in percentage. The images from two class label get maximum accuracy is 99.72% and maximum validation accuracy is 99.37% same as liquid’s image and the average value of accuracy 84.17% or higher after certain epochs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Use of artificial Intelligence in Construction

Use of Artificial Intelligence in Construction

引用

作者： Ali, Mohanad Metropolia University of Applied Sciences

学位级别：硕士

artificial Intelligence (AI) has been involved in the construction industry research since 1974, and it has gained exponential growth in research interest starting in the 21st century. artificial Intelligence is divided into many branches, such as Machine Learning (ML), artificial neural networks (ANN), Deep Learning (DL), Knowledge-Based Systems (KBSes), Computer Vision (CV) and image Recognition, Natural Language processing (NLP), Internet of Things (IoT) and Robotics. applications of the mentioned AI branches in the construction industry are discussed here, along with the challenges for their implementation. Moreover, five case studies discuss the involvement of different AI technologies and tools in project cost forecasting, report analysis, machinery activity, safety monitoring systems, construction monitoring and reporting, and remote construction site management. A literature review is formed to discuss the use of AI in construction. A simplified definition is given for each AI branch addressing the non-AI background readers, with examples given of the possible applications in different industries to provide a complete overview. applications and challenges of using AI technologies and tools in construction are also discussed and investigated from academic and practical perspectives. Five case studies are explained and discussed to verify the research argument.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unveiling Cetacean Voices: Entropy-Powered Spectrogram Denoising for Deep Learning applications 23rd

Unveiling Cetacean Voices: Entropy-Powered Spectrogram Denoi...

引用

23rd EPIA Conference on artificial Intelligence, EPIA 2024

作者： Bicudo, Francisco Cavaco, Sofia Freitas, Luís Verborgh, Philippe Esteban, Ruth Gauffier, Pauline Silva, Joaquim Nova School of Science and Technology Costa da Caparica Portugal Museu da Baleia da Madeira Caniçal Portugal

ISBN: (纸本)9783031734991

Acoustic monitoring of cetaceans is crucial for studying and conserving these animals and their environment. With the rising interest in deciphering dolphin and whale communication, and the promise shown by machine learning solutions in this field, the demand for gathering and processing large vocalization datasets is only increasing. In this paper, we propose an entropy-based spectrogram filtering method that removes noise naturally present in recordings of cetacean vocalizations. This method enhances the visual clarity of cetacean spectrograms, aiding biologists, and improves vocalization detection when using image-based convolutional neural networks. Its implementation focuses on efficiency, processing 256 times faster than similar filters. The resulting spectrograms achieve on average a 98.73% reduction in required storage space and allow for a segmentation technique that reduces labelling and classification times in machine learning solutions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Intelligent vision system for quality classification of airport lamp prisms 25

Intelligent vision system for quality classification of airp...

引用

25th IEEE Conference on Signal processing - Algorithms, Architectures, Arrangements, and applications (IEEE SPA)

作者： Suder, Jakub Podbucki, Kacper Marciniak, Tomasz Dabrowski, Adam Poznan Univ Tech Fac Automat Control Robot & Elect Engn Inst Automat Control & Robot Div Elect Syst & Signal Proc Jana Pawla II 24 PL-60965 Poznan Poland

ISBN: (数字)9788362065424

ISBN: (纸本)9788362065424

The article presents a concept of the analysis of mechanical wear of prisms in the in-pavement airport lamps. The solution is based on image processing technique that requires an appropriate selection of parameters due to the specificity of the objects. During the experimental tests, a database consisting of 316 photos of IDM airport lamps mounted in the airport areas was used. The proposed solution using an artificial neural network allows for the classification of lamps with an efficiency of 81.4%.

关键词： system airport lighting control neural networks artificial intelligence Hough transform

来源：评论

学校读者我要写书评

暂无评论

Compact Convolutional Transformers on Edge TPUs

Compact Convolutional Transformers on Edge TPUs

引用

Bildverarbeitung für die Medizin Workshop, BVM 2023

作者： Sun, Yipeng Kist, Andreas M. Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Germany

ISBN: (纸本)9783658416560

Medical image processing on edge devices is the key to local and efficient data processing. In the last decade, convolutional neural networks (CNNs) have dominated and achieved top performance in various medical imaging applications. However, CNNs are limited in their performance due to their inability to understand long-distance spatial relationships. The recently proposed vision transformer (ViT) learns long-distance spatial relationships of images based on self-attention, but these require large datasets for training. Hence, ViT-based architectures can be combined with CNNs to solve this problem. Yet, their use of edge devices has been barely explored. In this work, we investigate compact convolutional transformers (CCTs) and their ability to be deployed to edge devices. Using strategic design decisions, we were able to deploy CCT to Google Edge TPUs. In comparison to a reference CNN (ResNet50) that was also deployed to the Edge TPU, we reduce the model parameters by a factor of 35 and obtain a 7 × inference time speed-up while obtaining competitive accuracy. © 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolving Adaptive neural Network Optimizers for image Classification 1

引用

25th European Conference on Genetic Programming (EuroGP) Held as Part of EvoStar Conference

作者： Carvalho, Pedro Lourenco, Nuno Machado, Penousal Univ Coimbra Dept Informat Engn CISUC Polo 2 Pinhal Marrocos P-3030 Coimbra Portugal

ISBN: (数字)9783031020568

ISBN: (纸本)9783031020568;9783031020551

The evolution of hardware has enabled artificial neural networks to become a staple solution to many modern artificial Intelligence problems such as natural language processing and computer vision. The neural network's effectiveness is highly dependent on the optimizer used during training, which motivated significant research into the design of neural network optimizers. Current research focuses on creating optimizers that perform well across different topologies and network types. While there is evidence that it is desirable to fine-tune optimizer parameters for specific networks, the benefits of designing optimizers specialized for single networks remain mostly unexplored. In this paper, we propose an evolutionary framework called Adaptive AutoLR (ALR) to evolve adaptive optimizers for specific neural networks in an image classification task. The evolved optimizers are then compared with state-of-the-art, human-made optimizers on two popular image classification problems. The results show that some evolved optimizers perform competitively in both tasks, even achieving the best average test accuracy in one dataset. An analysis of the best evolved optimizer also reveals that it functions differently from human-made approaches. The results suggest ALR can evolve novel, high-quality optimizers motivating further research and applications of the framework.

关键词： Neuroevolution Adaptive Optimizers Structured Grammatical Evolution

来源：评论

学校读者我要写书评

暂无评论

A Review on Machine Learning Styles in Computer Vision-Techniques and Future Directions

引用

IEEE ACCESS 2022年 10卷 107293-107329页

作者： Mahadevkar, Supriya, V Khemani, Bharti Patil, Shruti Kotecha, Ketan Vora, Deepali R. Abraham, Ajith Gabralla, Lubna Abdelkareim Symbiosis Int Deemed Univ Symbiosis Inst Technol Pune 412115 Maharashtra India Symbiosis Int Deemed Univ Symbiosis Ctr Appl Artificial Intelligence Symbiosis Inst Technol Pune 412115 Maharashtra India Machine Intelligence Res Labs MIR Labs Auburn WA 98071 USA Princess Nourah Bint Abdulrahman Univ Coll Appl Dept Comp Sci & Informat Technol Riyadh 11671 Saudi Arabia

Computer applications have considerably shifted from single data processing to machine learning in recent years due to the accessibility and availability of massive volumes of data obtained through the internet and various sources. Machine learning is automating human assistance by training an algorithm on relevant data. Supervised, Unsupervised, and Reinforcement Learning are the three fundamental categories of machine learning techniques. In this paper, we have discussed the different learning styles used in the field of Computer vision, Deep Learning, neural networks, and machine learning. Some of the most recent applications of machine learning in computer vision include object identification, object classification, and extracting usable information from images, graphic documents, and videos. Some machine learning techniques frequently include zero-shot learning, active learning, contrastive learning, self-supervised learning, life-long learning, semi-supervised learning, ensemble learning, sequential learning, and multi-view learning used in computer vision until now. There is a lack of systematic reviews about all learning styles. This paper presents literature analysis of how different machine learning styles evolved in the field of artificial Intelligence (AI) for computer vision. This research examines and evaluates machine learning applications in computer vision and future forecasting. This paper will be helpful for researchers working with learning styles as it gives a deep insight into future directions.

关键词： Machine learning Computer vision Object detection artificial intelligence Machine learning algorithms image segmentation Feature extraction Machine learning techniques computer vision supervised learning multi-task learning object detection artificial intelligence image categorization zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

image Reconstruction Using Radio Tomography and artificial Intelligence in Tracking and Navigation Systems for Indoor applications

Image Reconstruction Using Radio Tomography and Artificial I...

引用

2023 International Interdisciplinary PhD Workshop, IIPhDW 2023

作者： Styla, Michal Kiczek, Bartlomiej Adamkiewicz, Przemyslaw Research & Development Department Rzeszów Poland Maria Curie-Sklodowska University Institute of Physics Lublin Poland Transport and Information Technology Department Lublin Poland

ISBN: (纸本)9781665410847

This thesis focuses on the technology for acquiring and processing localization data within the radio tomographic imaging technique supported by neural networks. The scope of work included both proprietary hardware solutions and computational algorithms. The result was a fully functional and self-contained system detecting living agents in confined spaces. Doing so does not require any signal source device located at the user. © 2023 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A Flexible and Efficient FPGA Accelerator for Various Large-Scale and Lightweight CNNs

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2022年第3期69卷 1185-1198页

作者： Wu, Xiao Ma, Yufei Wang, Meiqi Wang, Zhongfeng Nanjing Univ Sch Elect Sci & Engn Nanjing 210093 Peoples R China Peking Univ Inst Artificial Intelligence Beijing 100871 Peoples R China Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China

To enable efficient deployment of convolutional neural networks (CNNs) on embedded platforms for different computer vision applications, several convolution variants have been introduced, such as depthwise convolution (DWCV), transposed convolution (TPCV), and dilated convolution (DLCV). To address the utilization degradation issue occurred in a general convolution engine for these emerging operators, a highly flexible and reconfigurable hardware accelerator is proposed to efficiently support various CNN-based vision tasks. Firstly, to avoid workload imbalance of TPCV, a zero transfer and skipping (ZTS) method is proposed to reorganize the computation process. To eliminate the redundant zero calculations of TPCV and DLCV, a sparsity-alike processing (SAP) method is proposed based on weight-oriented dataflow. Secondly, the DWCV or pooling layers are configured to be directly executed after standard convolutions without external memory accesses. Furthermore, a programmable execution schedule is introduced to gain better flexibility. Finally, the proposed accelerator is evaluated on Intel Arria 10 SoC FPGA. Experimental results show state-of-the-art performance on both large-scale and lightweight CNNs for image segmentation or classification. Specifically, the accelerator can achieve a processing speed up to 339.9 FPS and computational efficiency up to 0.58 GOPS/DSP, which is 3.3x better than the prior art evaluated on the same network.

关键词： Convolution Kernel Standards Convolutional neural networks Field programmable gate arrays Task analysis Hardware acceleration Convolutional neural network depthwise separable convolution transposed convolution dilated convolution FPGA hardware accelerator

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：