检索结果-内蒙古大学图书馆

International Joint conference on neural networks (IJCNN)

作者： Cortes Pina, Oziel Villegas-Jimenez, Adolfo A. Aguilar-Canto, Fernando Gambino, Omar Juarez Calvo, Hiram Inst Politecn Nacl ESCOM Mexico City Mexico Inst Politecn Nacl CIC Mexico City Mexico

ISBN: (纸本)9798350359329;9798350359312

Deep neural networks have been successfully implemented in different areas of development and research, including image Classification, Natural Language processing, Time-Series Forecasting, and Bioinformatics, among others. However, its complex nature has raised questions about its internal functioning and decision-making, which is critical in different areas. This research seeks to explain the hidden representations of a neural network by using frameworks inspired by Neuroscience, which attempts to understand a very complex neural network, which is the human brain. In this approach, we investigated intermediate and low representation in four different networks: a simple dense Feedforward neural Network and the Convolutional neural networks LeNet-5, VGG-16, and ResNet50, by using similar inputs that were used in Neuroscience experiments. With this framework, we could detect highly selective cells to some of the inputs, remarking some interesting similarities between Biological and artificial neural networks.

关键词： Explainability Convolutional neural networks Hidden Semantics approach Neuroscience-Informed Interpretability

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural Network Approach for Early Skin Cancer Detection

引用

JOURNAL OF ELECTRICAL SYSTEMS 2023年第3期19卷 1-14页

作者： Raut, Roshani Gavali, Niraj Amate, Prathamesh Amode, Mihir Ajay Malunjkar, Shraddha Borkar, Pradnya Pimpri Chinchwad Coll Engn Dept Informat Technol Pune Maharashtra India Symbiosis Inst Technol Nagpur Maharashtra India

The field of medical image processing is rapidly adopting artificial intelligence. Its use is required for many applications in the healthcare industry. A machine can learn from experience without explicit programming thanks to computer education. It is an area within AI. Deep learning, a kind of machine learning, infers critical features for image processing via multiple layer processing and mathematical operations based on artificial neural networks. In the field of healthcare, which encompasses medicine and dentistry, artificial intelligence has several *** melanoma skin cancer identification is necessary for effective therapy. Melanoma, among the various types of skin cancer, has recently gained international recognition as the most deadly one since it is much more likely to spread to other body regions if detected and treated quickly. Clinical diagnosis of various ailments is increasingly using non-invasive medical computer vision or medical image processing. These methods offer an automatic image processing tool that makes it possible to examine the lesion quickly and precisely. The procedures used in this study included building a database of dermoscopy images, preprocessing, segmenting using thresholding, extracting statistical features using asymmetry, border, colour, diameter, etc., and choosing features based on the total dermoscopy score, principal component analysis (PCA), and convocation neural network classification (CNN). According to the findings, a classification accuracy of 90.1% was attained.

关键词： AlexNet Benign Convolutional neural Network Data pre-processing Feature extraction image Augmentation Malignant Maxpooling Training Testing Resnet VGG.

来源：评论

学校读者我要写书评

暂无评论

Tracking the Nodal Point of Weakly Electric Fish Using artificial neural networks 31

Tracking the Nodal Point of Weakly Electric Fish Using Artif...

引用

31st IEEE conference on Signal processing and Communications applications (SIU)

作者： Catalbas, Bahadir Elikuru, Dogukaan Aydin, Emin Yusuf Uyanik, Ismail Hacettepe Univ Elekt & Elekt Muhendisligi Bolumu Ankara Turkiye Yildiz Tekn Univ Kontrol & Otomasyon Muhendisligi Bolumu Istanbul Turkiye

ISBN: (纸本)9798350343557

In living beings, there is a closed-loop system called sensorimotor transformation, in which the signals received by the sensory organs from the environment are processed in the nervous system, and the necessary motor signals are transmitted to the muscular system. Unfortunately, the closed-loop nature of the structure makes it difficult to decipher the relationship between inputs and outputs. Since the nodal point on the anal fin of the weakly electric fish (Eigenmannia virescens) may be an output of the sensorimotor control system, precisely monitoring its position is important. The method used in the literature to find the nodal point so far is to mark each video frame manually. However, manual marking creates a significant workload and causes a waste of time. This study aims to determine the position of the node that has been manually marked so far by using artificial neural networks more easily and effectively.

关键词： artificial neural network deep learning weakly electric fish sensorimotor control

来源：评论

学校读者我要写书评

暂无评论

AI Innovator: Text to image Generation using GAN

AI Innovator: Text to Image Generation using GAN

引用

2024 IEEE International Students' conference on Electrical, Electronics and Computer Science, SCEECS 2024

作者： Nimbarte, Mrudula Hussain, Alfiya Budhlani, Kanak Bansod, Chirag Ramdham, Mayur Kanhe, Om Khullar, Amit S.B. Jain Institute of Technology Management and Research Department of Computer Science and Engineering MS Nagpur India

ISBN: (纸本)9798350348460

This review provides a comprehensive review of the latest approaches and advances in text-to-image processing using artificial neural networks (GANs). The work under review uses GAN architecture, where generators and classifiers work together to extract corresponding images from descriptions. This research includes a comprehensive review of the GAN framework, delving into the complexities of the generator and discrimination during training. The project solves problems related to converting text input into visual images using a combination of natural language processing and computer vision. This article reviews the main concepts of the architecture as well as the use of advanced neural networks for text understanding and image synthesis. Particular attention is paid to the optimization process the generator uses to improve the quality and integrity of the resulting images. Additionally, the review highlights the evolution of different labels and discusses their implications for real-world applications. © 2024 IEEE.

关键词： Adversarial Training Computer Vision Generative Adversarial networks (GANs) image Synthesis Multimodal Learning Natural Language processing (NLP) neural Network Architecture Text to image Generation

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Medical Data: Current Methods, Limitations, and Future Directions

引用

ACM COMPUTING SURVEYS 2025年第6期57卷 1-46页

作者： Hossain, Md Imran Zamzmi, Ghada Mouton, Peter r. Salekin, Md Sirajus Sun, Yu Goldgof, Dmitry Univ S Florida Dept Comp Sci & Engn ENB 4202 E Fowler Ave Tampa FL 33620 USA SRC Biosci 1810 W Kennedy Blvd Tampa FL 33606 USA

With the power of parallel processing, large datasets, and fast computational resources, deep neural networks (DNNs) have outperformed highly trained and experienced human experts in medical applications. However, the large global community of healthcare professionals, many of whom routinely face potentially life-or-death outcomes with complex medicolegal consequences, have yet to embrace this powerful technology. The major problem is that most current AI solutions function as a metaphorical black-box positioned between input data and output decisions without a rigorous explanation for their internal processes. With the goal of enhancing trust and improving acceptance of artificial intelligence- (AI) based technology in clinical medicine, there is a large and growing effort to address this challenge using eXplainable AI (XAI), a set of techniques, strategies, and algorithms with an explicit focus on explaining the "hows and whys" of DNNs. Here, we provide a comprehensive review of the state-of-the-art XAI techniques concerning healthcare applications and discuss current challenges and future directions. We emphasize the strengths and limitations of each category, including image, tabular, and textual explanations, and explore a range of evaluation metrics for assessing the effectiveness of XAI solutions. Finally, we highlight promising opportunities for XAI research to enhance the acceptance of DNNs by the healthcare community.

关键词： Explainability medical data responsible AI deep neural networks pretable AI

来源：评论

学校读者我要写书评

暂无评论

Topological Insulator Optoelectronic Synapses for High-Accuracy Binary image Recognition using Recurrent neural networks

引用

ADVANCED OPTICAL MATERIALS 2023年第2期11卷

作者： Wan, Zhengfen Zhang, Qiwen Hu, Fangzhen Dong, Yibo Li, Runze Hu, Liangchen Xie, Yiyang Yue, Zengji Chen, Xi Gu, Min Univ Shanghai Sci & Technol Inst Photon Chips Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Ctr Artificial Intelligence Nanophoton Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China Beijing Univ Technol Key Lab Optoelect Technol Minist Educ Beijing 100124 Peoples R China

artificial optoelectronic synapses have drawn tremendous attention in neuromorphic computing due to their exceptional properties of incorporating optical-sensing and synaptic functions. However, the complex fabrication processes and device architectures greatly limit their applications. More importantly, artificial neural networks (ANNs) commonly implemented with optoelectronic synapses cannot take full advantage of the time-dependent data of synaptic devices, resulting in defective accuracies. Here, facile two-terminal optoelectronic synapses based on topological insulator Sb2Te3 films are fabricated, which exhibit significant photocurrent responses, owing to the efficient light-matter interaction in bulk and the topological surface state of Sb2Te3. The performance of Sb2Te3 devices can be tuned both optically and electrically. Typical characteristics of synapses, such as paired-pulse facilitation, short-term memory, long-term memory, and learning behavior, have been demonstrated. With the establishment of recurrent neural networks (RNNs) that are committed to processing temporal data, the as-fabricated synapse devices are employed for binary image recognition of handwritten numbers "0" and "1". The recognition accuracy of RNNs can reach as high as 100%, which is dramatically higher than those of ANNs. The effective employment of temporal data with RNNs ensured high recognition accuracy. These Sb2Te3 optoelectronic synapses with RNNs indicate the great potential for developing high-performance brain-inspired neuromorphic computing.

关键词： image recognition neuromorphic computing optoelectronic synapses recurrent neural networks Sb Te-2 (3) films topological insulators

来源：评论

学校读者我要写书评

暂无评论

Revisiting DCT in Deep Learning Era: An Initial Denoising Application 32

Revisiting DCT in Deep Learning Era: An Initial Denoising Ap...

引用

32nd IEEE Signal processing and Communications applications conference (SIU)

作者： Karaoglu, Hasan H. Eksioglu, Ender M. Istanbul Tech Univ Elekt & Haberlesme Muhendisligi Bolumu Istanbul Turkiye

ISBN: (纸本)9798350388978;9798350388961

In the classical era of image denoising, the methods working in transform domain have achieved high performance results. However, most of the deep neural networks that have been proposed in the last decade and have shown better noise removal performance try to denoise the noisy image in pixel domain. In deep learning literature, there are few deep neural networks that work in transform domain. Most of them have not chosen the discrete cosine transform (DCT), which is known to provide a very good representation for most images. This is the result of convolution layer, which is often used in deep networks, searching in vain for a relationship between neighboring values of an image's uncorrelated global and block DCT coefficients. On the other hand, it is known that working with transform coefficients of overlapped image blocks improves noise removal performance. Recent studies have shown that the convolution of an image with 2D DCT basis images is a meaningful ordering of the DCT coefficients of overlapping image blocks. Hence, in this paper, a deep neural network is proposed to remove noise in the DCT domain. Experiments on color images indicate that the proposed network is quantitatively and qualitatively successful in noise removal.

关键词： image denoising deep learning discrete cosine transform

来源：评论

学校读者我要写书评

暂无评论

Deep spiking neural networks based on model fusion technology for remote sensing image classification

引用

ENGINEERING applications OF artificial INTELLIGENCE 2025年 142卷

作者： Niu, Li-Ye Wei, Ying Zhao, Liping Hu, Keli Zhejiang Chinese Med Univ Zhejiang Prov Hosp Chinese Med Dept Radiol Affiliated Hosp 1 Hangzhou 310006 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Shaoxing Univ Dept Comp Sci & Engn Shaoxing 312000 Peoples R China

The spiking neural network (SNN) based on brain inspiration, as the third-generation neural network, has attracted great research interest due to its ultra-low power event-driven data processing method. How to obtain high-accuracy deep networks has always been a challenge in the field of SNN. At present, there are two main methods for training deep spiking neural networks (SNNs). The first is the spike-based spatiotemporal backpropagation (STBP), and the other indirect is to convert the trained artificial neural network (ANN) into SNN (ANN-SNN). Algorithms that directly train SNNs are usually inefficient, while the ANN-SNN-based models require along inference time and also suffer from performance losses. The model fusion technology (MFT) proposed in this paper, combined with ANN-SNN and STBP, provides a new training paradigm for obtaining deep SNNs. We propose a bilateral multi-strength integrate-and-fire (BM-IF) spiking neuron for ANN-SNN to simplify the conversion operation. Under the same network architecture and encoding time window, the ResNet34 based on our algorithm achieved State-of-the-art (SOTA) in imageNet. At the same time, we combined transfer learning methods to achieve SOTA results on three remote sensing scene classification datasets. Our results also indicate that the MFT-based SNN outperforms the optimal inference accuracy provided by ANNSNN in terms of network architecture and dataset inference time steps reduced by 512-1250 times. It can be seen that this algorithm provides a low-latency and high-precision training scheme for the development of deep SNN.

关键词： Spiking neural network Model fusion technology Low-latency High-precision Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Invisible and Multi-triggers Backdoor Attack Approach on Deep neural networks through Frequency Domain

Invisible and Multi-triggers Backdoor Attack Approach on Dee...

引用

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

作者： Sun, Fengxue Pei, Bei Chen, Guangyong Southeast Univ Sch Cyber Sci & Engn Nanjing Peoples R China Natl Engn Res Ctr Classified Protect & Safeguard Shanghai Peoples R China

ISBN: (纸本)9798350350920

In recent years, the security of deep neural networks (DNNs) has become a research hotspot with widespread deployments of machine learning models in our daily life. Backdoor attack is an emerging security threat to DNNs, where the infected model will output malicious targets for the images containing specific triggers. However, most existing backdoor attack approaches have only single trigger, and the triggers are often visible to human eyes. In order to overcome these limitations, in this paper, we propose an invisible and multi-triggers backdoor attack (IMT-BA) approach to simultaneously generate four invisible triggers. Firstly, in our IMT-BA approach, we divide the whole images into four blocks and apply Discrete Cosine Transform (DCT) algorithm to generate four invisible triggers aiming at four targets. Secondly, our IMT-BA approach can be easily deployed in real world without any knowledge of the hyperparameters and architectures of the DNNs models. Finally, we do the experiments with MNIST and CIFAR-10 datasets and the experiment results show our IMT-BA approach can fool both DNNs models and Human Visual System (HVS) with high success rate.

关键词： artificial intelligence security backdoor attack frequency domain discrete cosine transform

来源：评论

学校读者我要写书评

暂无评论

Fault detection of induction machine using artificial neural networks 8

Fault detection of induction machine using artificial neural...

引用

8th IEEE International conference on image and Signal processing and their applications, ISPA 2024

作者： Bentrad, Moutaz Bellah Ghoggal, Adel Bahi, Tahar Bouziane, Seif Eddine LGEB Mohamed Khider University Electrical Department Annaba Algeria LGEB Mohamed Khider University Electrical Department Biskra Algeria LASA Badji Mokhtar University Electrical Department Annaba Algeria National School of Artificial Intelligence Intelligent Systems Engineering Department Algiers Algeria

ISBN: (纸本)9798350309249

The diagnosis and monitoring of industrial machinery faults is crucial to the Industrial Revolution but is frequently difficult and labor-intensive. Due to its quick computation, accurate prediction and robustness in performance, the use of artificial intelligence techniques has become a crucial component of condition monitoring of rotating machinery. This paper aims to use the artificial intelligence (neural network technique) to be able to detect and identify air gap eccentricity (static and mixed) and its influence on the stator current signature, the aim is to demonstrate the reliability and accuracy of these techniques to help us make the decision, The achieved simulation results allow distinguishing the types of eccentricity based on the Motor Current Signature Analysis technique data. © 2024 IEEE.

关键词： Induction machine

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：