检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Shiqi Li, Yuhang Chen, Hanlong Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States

Generative models cover various application areas, including image, video and music synthesis, natural language processing, and molecular design, among many others. As digital generative models become larger, scalable inference in a fast and energy-efficient manner becomes a challenge. Here, we present optical generative models inspired by diffusion models, where a shallow and fast digital encoder first maps random noise into phase patterns that serve as optical generative seeds for a desired data distribution;a jointly-trained free-space-based reconfigurable decoder all-optically processes these generative seeds to create novel images (never seen before) following the target data distribution. Except for the illumination power and the random seed generation through a shallow encoder, these optical generative models do not consume computing power during the synthesis of novel images. We report the optical generation of monochrome and multicolor novel images of handwritten digits, fashion products, butterflies, and human faces, following the data distributions of MNIST, Fashion MNIST, Butterflies-100, and Celeb-A datasets, respectively, achieving an overall performance comparable to digital neural network-based generative models. To experimentally demonstrate optical generative models, we used visible light to generate, in a snapshot, novel images of handwritten digits and fashion products. These optical generative models might pave the way for energy-efficient, scalable and rapid inference tasks, further exploiting the potentials of optics and photonics for artificial intelligence-generated content. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

基于离体神经网络的生物智能计算:关键技术与研究现状(特邀)

引用

红外与激光工程 2025年第3期54卷 93-113,I0001页

作者：杜金帅邓寅曹世阳陆泽营李杰韩卓周晋民王棵桂丽丽徐坤北京邮电大学信息光子学与光通信全国重点实验室北京100876

随着人工智能(AI)的快速发展,其高能耗、低解释性和灵活性不足等问题日益凸显。生物神经网络(Biological neural networks,BNN)因其基于真实生物神经元的动态可塑性和自适应性,成为突破AI瓶颈的重要研究方向。离体培养的BNN通过精确的... 详细信息

随着人工智能(AI)的快速发展,其高能耗、低解释性和灵活性不足等问题日益凸显。生物神经网络(Biological neural networks,BNN)因其基于真实生物神经元的动态可塑性和自适应性,成为突破AI瓶颈的重要研究方向。离体培养的BNN通过精确的培养技术和先进的调控手段,为理解生物大脑的信息处理机制以及开发新型智能系统提供了实验平台。文中系统地综述了离体BNN的培养方法及功能优化技术,包括二维和三维培养方式,以及模块化网络构建与连接调控方法。详细探讨了电学刺激、光学刺激和化学刺激等信号输入技术,以及细胞内外动作电位记录、钙荧光成像等信号输出技术。此外,还分析了BNN在静态任务(如语音识别)和实时交互任务(如神经机器人控制)中的应用实例,展示了其在动态学习、复杂模式识别和实时任务适应中的潜力。最后,总结了当前基于BNN的生物智能计算研究的主要挑战,提出了未来研究的方向,希望为未来生物智能计算的研究与发展提供一定启示。

关键词：生物神经网络离体培养双向通信技术生物智能计算

来源：评论

学校读者我要写书评

暂无评论

Cloud Resource Load Prediction Based on EEMD-LSTM

Cloud Resource Load Prediction Based on EEMD-LSTM

引用

Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), IEEE International Conference on

作者： Xuemei Cheng Xiaojiang Ye Zhijian Hou Yunhui Zhang School of Optical Information and Energy Engineering Wuhan Institute of Technology Wuhan China School of Mechanical and Electrical Engineering Shenzhen Polytechnic University Shenzhen China

ISBN: (数字)9798350378542

ISBN: (纸本)9798350378559

With the rapid advancement of cloud computing, accurate load prediction has become essential for optimizing system performance. The nonlinear and non-stationary characteristics of cloud resource load data have increased the complexity of prediction tasks. To address this challenge, this paper proposes a multi-input multi-output load prediction model based on Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM) networks. The model reduces data complexity through EEMD decomposition while effectively capturing the temporal dependencies in the sequence data using LSTM. Experiments conducted on publicly available cluster datasets from Alibaba demonstrate that the EEMD-LSTM model significantly outperforms traditional models, such as LSTM, Recurrent neural network (RNN), and Multi-Layer Perceptron (MLP), in predicting CPU and memory usage, as evaluated by metrics including Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the Coefficient of Determination (R2).

关键词： Cloud computing Adaptation models Accuracy Recurrent neural networks Computational modeling Predictive models Data models Complexity theory Long short term memory Load modeling

来源：评论

学校读者我要写书评

暂无评论

Handwritten Character Recognition with Stable and Adaptable Convolutional neural network 2

Handwritten Character Recognition with Stable and Adaptable ...

引用

2nd International Conference on Artificial Intelligence, Automation, and High-Performance computing, AIAHPC 2022

作者： Han, Feichi Wenzheng College Soochow University Suzhou China

ISBN: (纸本)9781510657717

Handwritten character recognition is widely used in mail collection and classification, note sorting and filing, financial data identification and analysis, etc. Current machine learning methods for handwritten character recognition mainly include Random Forest (RF) and Support Vector Machine (SVM). However, the performance of these methods compromises a lot due to high noise, non-linearity, and unobvious feature values in handwritten character images. This paper presents a stable and adaptable Convolutional neural network (CNN) to recognize handwritten characters. First, this paper preprocesses the images by noise reduction, one-hot encoding, and contrast enhancement to increase the recognizability. Then, this paper combines the structures of several CNN classic models to construct a CNN model with strong adaptability and high stability. This CNN model loops through a combination of a convolutional layer, a pooling layer, and a Dropout layer, which realizes the full connection of local features and reduces the amounts of parameters and data complexity. The Dense layers map the flattened image data to the output space by extracting the correlation between the features. Each layer in this CNN combines with Relu-based activation functions to perform nonlinear mapping, alleviating problems such as gradient disappearance and overfitting. The proposed CNN is compared with RF and SVM on the English Handwritten Characters dataset with accuracy and confusion matrix. The recognition accuracies of RF, SVM and CNN are 0.90, 0.92 and 0.96, respectively. RF and SVM confuse multiple characters, while CNN only generates a small number of confusion on the characters G and S. In the test with actual handwritten characters as samples, this CNN also shows higher recognition accuracy and fewer confused characters than RF and SVM. In addition, this paper compares and evaluates this CNN with other representative CNN models. The experimental result shows that the proposed CNN has a greate

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

JSVulExplorer：A JavaScript Vulnerability Detection Model Based on Transfer Learning 5

JSVulExplorer：A JavaScript Vulnerability Detection Model Ba...

引用

5th International Conference on Computer Information Science and Artificial Intelligence, CISAI 2022

作者： Chen, Shengquan Jiang, Nan Wu, Zheng Wang, Zichen Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Beijing100124 China

ISBN: (纸本)9781510662520

Software vulnerabilities will make the system vulnerable to attack, affect the reliability of the software and cause information leakage, which will have a huge impact on enterprises or individuals. Vulnerabilities are inevitable in software development engineering. Therefore, relying on some methods or tools for continuous vulnerability analysis of code is the solution to minimize software vulnerabilities. We propose a neural network model - JSVulExplorer for static vulnerability analysis of the dynamic programming language JavaScript. The JSVulExplorer focuses on feature enhancement of data. We use pre-training to learn the semantic similarity between code slices, utilize abstract syntax trees to generate path information, and design positional encoding to use the path information. Based on transfer learning, we combine the pre-trained model with path information to improve vulnerability detection performance. Experiments show that JSVulExplorer has significantly improved precision and recall compared to previous models. It is verified that the dynamic event-based programming language can also use the static analysis method for vulnerability detection. © 2023 SPIE.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Research on Sleep Staging Method Based on Multi-Scale Convolution and Self-Attention Mechanism 2

Research on Sleep Staging Method Based on Multi-Scale Convol...

引用

2nd International Conference on Biomedical and Intelligent Systems, IC-BIS 2023

作者： Pan, Dongdong Li, Yingying School of Computer and Artificial Intelligence Zhengzhou University China State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University China

ISBN: (纸本)9781510666733

Sleep is a very important physiological process for humans, and sleep staging is an important basis for evaluating sleep quality and diagnosing sleep-related diseases. Manual sleep staging is time-consuming and laborious, and the staging results are easily affected by subjective factors. Therefore, the research on automatic sleep staging models has extremely high research value and clinical application value. This paper proposes a sleep staging method based on multi-scale one-dimensional convolutional neural network and self-attention mechanism. The attention mechanism mines the channel correlation and temporal correlation of different channels respectively. This paper selects the sleep data of 153 normal subjects in the public dataset Sleep-EDF for model training and testing. The average staging accuracy rate was 84.5%, and the consistency test value was 0.781, which was better than the consistency test value of 0.75 for the inter-physician score. The experimental results show that the algorithm model in this paper has a high staging effect, can make full use of sleep data, and has important research significance for assisting clinicians in rapid sleep staging. © 2023 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Regularization Strength Impact on neural network Ensembles 5

Regularization Strength Impact on Neural Network Ensembles

引用

5th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2022

作者： Njieutcheu Tassi, Cedrique Rovile Börner, Anko Triebel, Rudolph Institute of Optical Sensor Systems Germany Institute of Robotics and Mechatronics Germany

ISBN: (纸本)9781450398343

In the last decade, several approaches have been proposed for regularizing deeper and wider neural networks (NNs), which is of importance in areas like image classification. It is now common practice to incorporate several regularization approaches in the training procedure of NNs. However, the impact of regularization strength on the properties of an ensemble of NNs remains unclear. For this reason, the study empirically compared the impact of NNs built based on two different regularization strengths (weak regularization (WR) and strong regularization (SR)) on the properties of an ensemble, such as the magnitude of logits, classification accuracy, calibration error, and ability to separate true predictions (TPs) and false predictions (FPs). The comparison was based on results from different experiments conducted on three different models, datasets, and architectures. Experimental results show that the increase in regularization strength 1) reduces the magnitude of logits;2) can increase or decrease the classification accuracy depending on the dataset and/or architecture;3) increases the calibration error;and 4) can improve or harm the separability between TPs and FPs depending on the dataset, architecture, model type and/or FP type. © 2022 ACM.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: A modified fuzzy histogram of optical flow for emotion classification (Retracted Article)

引用

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED computing 2021年第3期12卷 3601-3608页

作者： Ragupathy, P. Vivekanandan, P. Pk Coll Engn & Technol Dept Comp Sci & Engn Coimbatore Tamil Nadu India

Human beings tend to express various emotions based on the activities. The criticality of facial expression has been recognized widely in the social interaction along with the social intellect. Human perception is subjective in nature and this makes the classification of emotion an extremely challenging problem. The mood, personality, age, and environment have a major influence on the perception of emotion. Facial expressions are a key to emotion;various studies devote on emotion classification based on facial expression. For the identification of these emotions, there is a mixture of models that make use of the feature representation that are gradient based, a mixture of various dynamic textures along with contextual information. In this work, histogram of optical flow (HOF) was used for the extraction of features and a neural network for bringing about an improvement to the accuracy of classification. With the availability of big data analytics, there has been a major increase in the power of computation in terms of analysing live video data, huge number of images and faster processing which is critical for emotion classification. The work has investigated efficacy of the flow of HOF and proposed a modified fuzzy histogram of optical flow. For choosing optimal rules in fuzzy system, heuristic method namely, charged system search was used. The results have proved that there has been a significant improvement to the methodology proposed.

关键词： Emotion recognition neural network (NN) Histogram of optical flow (HOF) Fuzzy and charged system search (CSS)

来源：评论

学校读者我要写书评

暂无评论

Artifact Reduction in Phase Imaging by the Transport of Intensity Equation Using a Convolutional neural network

Artifact Reduction in Phase Imaging by the Transport of Inte...

引用

Electrical, Computer and Energy Technologies (ICECET), International Conference on

作者： Alireza Sheikhsofla Shane Carney Alexander Khmaladze Jonathan Petruccelli Department of Physics SUNY University at Albany Albany USA

ISBN: (数字)9798350395914

ISBN: (纸本)9798350395921

In quantitative phase imaging (QPI), various methodologies are employed to generate three-dimensional representations of samples, particularly in the field of biology, facilitating the tracking of cellular parameters like volume. A recent advancement in QPI involves the utilization of partially coherent light to mitigate coherent noise, coupled with the solution of the phase through solution of the (partial differential) transport of intensity equation (TIE), a rapid and easily implemented technique. Despite the numerous advantages associated with phase imaging based on TIE, conventional solution methods often produce significant phase artifacts when samples extend beyond the field of view due to a lack of unknown boundary values. To address this issue, we have trained a convolutional neural network (CNN) to produce solutions to the TIE using a dataset comprising conventional TIE phase images verified through digital holographic microscopy. We subsequently compared CNN's predictions with those of the conventional TIE solver, particularly focusing on cases where the conventional solutions suffered from artifacts. We additionally assessed the performance of the trained model using images obtained in a Raman microscope, a system from which TIE images suffer from artifacts due to poor alignment. Our findings demonstrate that CNN's phase predictions outperform those of the TIE solver, particularly in scenarios involving extended samples or poor optical alignment.

关键词： Integrated optics Spectroscopy optical microscopy Microscopy Low frequency noise optical computing Holography optical imaging Mathematical models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection through Synergistic Combination of Image Processing and Deep CNN using MATLAB

Glaucoma Detection through Synergistic Combination of Image ...

引用

Emerging Technology (INCET), International Conference for

作者： B. Subbarayudu Harshitha Yadalam Jeevana Seepiri Jayalakshmi Bhogathi dept. ECE of Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

This study introduces an innovative Glaucoma detection framework that significantly outperforms existing methodologies by employing a hybrid approach combining advanced image processing and Convolutional neural networks (CNN). The key to our approach is the precise segmentation of the optic cup using state-of-the-art image processing algorithms, which allows the CNN to accurately identify glaucomatous changes from retinal images. Our Glaucoma detection method had 95.45% sensitivity, 93.59% specificity, and 94.44% accuracy, surpassing other contemporary techniques such as the SVM Classifier, which showed an accuracy of 90%, and a Convolutional neural network approach by other researchers with an accuracy of 91.52%. These results affirm the potential of our method as a highly reliable tool for early Glaucoma diagnosis in clinical practice, promoting better patient outcomes through earlier treatment interventions. This study introduces an opportunity for enhancing glaucoma screening and early treatments through using of MATLAB software.

关键词： Glaucoma Training Accuracy neural networks optical computing optical imaging Mathematical models

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：