检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2023年第1期24卷 10909-10959页

作者： Xiaoyu Wang Martin Benning Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge UK School of Mathematical Sciences Queen Mary University of London London UK

We introduce a novel mathematical formulation for the training of feed-forward neural networks with (potentially non-smooth) proximal maps as activation functions. This formulation is based on Bregman distances and a key advantage is that its partial derivatives with respect to the network's parameters do not require the computation of derivatives of the network's activation functions. Instead of estimating the parameters with a combination of first-order optimisation method and back-propagation (as is the state-of-the-art), we propose the use of non-smooth first-order optimisation methods that exploit the specific structure of the novel formulation. We present several numerical results that demonstrate that these training approaches can be equally well or even better suited for the training of neural network-based classifiers and (denoising) autoencoders with sparse coding compared to more conventional training frameworks.

关键词： lifted network training distributed optimisation Bregman distances sparse autoencoder denoising autoencoder classification compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Fault Detection based on Deep Learning for Digital VLSI Circuits

引用

Procedia Computer Science 2021年 194卷 122-131页

作者： Lamya Gaber Aziza I. Hussein Mohammed Moness Computers and Systems Eng. Dept. Minia University Minia 61111 Egypt Electrical and Computer Eng. Dept. Effat University Jeddah 22332 Saudi Arabia

As growing complexity of digital VLSI circuits, fault detection and correction processes have been the most crucial phases during IC design. Many CAD tools and formal approaches have been used for debugging and localizing different kinds of design bugs. However, the search space explosion problem remains the main problem for IC designers. Recently, Artificial intelligence and machine learning models have been expanded in feature extraction and reduction models. In this paper, we introduce a new fault detection model based on deep learning for extracting features and detecting faults from large-sized digital circuits. The main goal of the proposed model is to avoid the search space using stacked sparse autoencoder, a specific type of artificial neural network. The model consists of three phases: test pattern generation using ATALANTA software, feature reduction using SSAE and classification for fault detection. Test vectors are utilized in SSAE as a training data for unsupervised learning phase. The performance of feature extraction is tested by changing the architecture of SSAE network and sparsity constraint. The proposed algorithm has been implemented using eight combinational digital circuits from ISCAS’85. From experimental results, the maximum fault coverage using ATALANTA tool delivers around 99.2% using ISCAS’85. In addition, the maximum validation accuracy of proposed SSAE model delivers around 99.7% in feature reduction phase.

关键词： Design Debugging sparse autoencoder ML Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Predicting the potential associations between circRNA and drug sensitivity using a multisource feature-based approach

引用

JOURNAL OF CELLULAR AND MOLECULAR MEDICINE 2024年第19期28卷 e18591页

作者： Yin, Shuaidong Xu, Peng Jiang, Yefeng Yang, Xin Lin, Ye Zheng, Manyu Hu, Jinpeng Zhao, Qi Univ Sci & Technol Liaoning Sch Comp Sci & Software Engn Anshan 114051 Peoples R China Univ Sci & Technol Liaoning Sch Elect & Informat Engn Anshan Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China

The unique non-coding RNA molecule known as circular RNA (circRNA) is distinguished from conventional linear RNA by having a longer half-life, greater degree of conservation and inherent solidity. Extensive research has demonstrated the profound impact of circRNA expression on cellular drug sensitivity and therapeutic efficacy. There is an immediate need for the creation of efficient computational techniques to anticipate the potential correlations between circRNA and drug sensitivity, as classical biological research approaches are time-consuming and costly. In this work, we introduce a novel deep learning model called SNMGCDA, which aims to forecast the relationships between circRNA and drug sensitivity. SNMGCDA incorporates a diverse range of similarity networks, enabling the derivation of feature vectors for circRNAs and drugs using three distinct calculation methods. First, we utilize a sparse autoencoder for the extraction of drug characteristics. Subsequently, the application of non-negative matrix factorization (NMF) enables the identification of relationships between circRNAs and drugs based on their shared features. Additionally, the multi-head graph attention network is employed to capture the characteristics of circRNAs. After acquiring the characteristics from these three separate components, we combine them to form a unified and inclusive feature vector for each cluster of circRNA and drug. Finally, the relevant feature vectors and labels are inputted into a multilayer perceptron (MLP) to make predictions. The outcomes of the experiment, obtained through 5-fold cross-validation (5-fold CV) and 10-fold cross-validation (10-fold CV), demonstrate SNMGCDA outperforms five other state-of-art methods in terms of performance. Additionally, the majority of case studies have predominantly confirmed newly discovered correlations by SNMGCDA, thereby emphasizing its reliability in predicting potential relationships between circRNAs and drugs.

关键词： circRNA drug graph neural network non-negative matrix factorization sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

A deep feature extraction method for bearing fault diagnosis based on empirical mode decomposition and kernel function

引用

ADVANCES IN MECHANICAL ENGINEERING 2018年第9期10卷

作者： Wang, Fengtao Deng, Gang Liu, Chenxi Su, Wensheng Han, Qingkai Li, Hongkun Dalian Univ Technol Sch Mech Engn Dalian 116024 Peoples R China Jiangsu Prov Special Equipment Safety Supervis In Wuxi Branch Wuxi Peoples R China

To avoid catastrophic failures in rotating machines, it is of great significance to continuously monitor and diagnose the running state of rolling bearings. In this article, a deep feature extraction method for rolling bearing fault diagnosis based on empirical mode decomposition and kernel function is proposed. First, the vibration signals under different states of rolling bearing are decomposed by empirical mode decomposition. Second, to extract more representative high-level features, the obtained intrinsic mode functions are preprocessed with singular value decomposition to acquire singular value parameters, which are regarded as the inputs of the proposed stacked kernel sparse autoencoder network. The proposed method does not depend on prior knowledge of fault diagnosis and even does not need the signal denoising processing, simplifying the traditional process of feature extraction of rolling bearing fault diagnosis. To validate the superiority of the proposed diagnosis network, experiments and comparisons have been made as well. The achieved results demonstrated that the proposed empirical mode decomposition and stacked kernel sparse autoencoder-based diagnosis method has a superior performance in rolling bearing fault diagnosis.

关键词： Rolling bearing fault diagnosis empirical mode decomposition sparse autoencoder kernel function

来源：评论

学校读者我要写书评

暂无评论

Hybrid evolutionary approach for Devanagari handwritten numeral recognition using Convolutional Neural Network

引用

Procedia Computer Science 2018年 125卷 525-532页

作者： Adarsh Trivedi Siddhant Srivastava Apoorva Mishra Anupam Shukla Ritu Tiwari Soft Computing and Expert System Laboratory ABV-Indian Institute of Information Technology Gwalior 474015 India

In recent years, deep learning has been extensively used in both supervised and unsupervised learning problems. Among the deep learning models, CNN has outperformed all others for object recognition task. Although CNN achieves exceptional accuracy, still a huge number of iterations and chances of getting stuck in local optima makes it computationally expensive to train. Genetic Algorithm is a metaheuristic approach inspired by the theory of natural selection and has been used for solving both bounded and unbounded optimization problems by a large success. To handle these issues, we have developed a hybrid deep learning model using Genetic Algorithm and L-BFGS method for training CNN. To test our model, we have taken the Devanagari handwritten numeral dataset. Our results show that GA assisted CNN produces better results than non-GA assisted CNN. This study concludes that evolutionary technique can be used to train CNN more efficiently.

关键词： Convolutional Neural Network Genetic Algorithm sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised autoencoder : A Joint Approach of Representation And Classification 7

Semi-Supervised Autoencoder : A Joint Approach of Representa...

引用

7th International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Wu Haiyan Yang Haomin Li Xueming Ren Haijun Chongqing Univ Coll Comp Sci Chongqing Peoples R China

ISBN: (纸本)9781509000760

Recent years have witnessed the significant success of representation learning and deep learning in various prediction and recognition applications. Most of these previous studies adopt the two-phase procedures, namely the first step of representation learning and then the second step of supervised learning. In this process, to fit the training data the initial model weights, which inherits the good properties from the representation learning in the first step, will be changed in the second step. In other words, the second step leans better classification models at the cost of the possible deterioration of the effectiveness of representation learning. Motivated by this observation we propose a joint framework of representation and supervised learning. It aims to learn a model, which not only guarantees the "semantics" of the original data from representation learning but also fit the training data well via supervised learning. Along this line we develop the model of semi-supervised autoencoder under the spirit of the joint learning framework. The experiments on various data sets for classification show the significant effectiveness of the proposed model.

关键词： semi-supervised autoencoder deep learning logistic regression sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

GesID: 3D Gesture Authentication Based on Depth Camera and One-Class Classification

引用

SENSORS 2018年第10期18卷 3265-3265页

作者： Wang, Xuan Tanaka, Jiro Waseda Univ Grad Sch Informat Prod & Syst Wakamatsu Ward 2-7 Hibikino Kitakyushu Fukuoka 8080135 Japan

Biometric authentication is popular in authentication systems, and gesture as a carrier of behavior characteristics has the advantages of being difficult to imitate and containing abundant information. This research aims to use three-dimensional (3D) depth information of gesture movement to perform authentication with less user effort. We propose an approach based on depth cameras, which satisfies three requirements: Can authenticate from a single, customized gesture;achieves high accuracy without an excessive number of gestures for training;and continues learning the gesture during use of the system. To satisfy these requirements respectively: We use a sparse autoencoder to memorize the single gesture;we employ data augmentation technology to solve the problem of insufficient data;and we use incremental learning technology for allowing the system to memorize the gesture incrementally over time. An experiment has been performed on different gestures in different user situations that demonstrates the accuracy of one-class classification (OCC), and proves the effectiveness and reliability of the approach. Gesture authentication based on 3D depth cameras could be achieved with reduced user effort.

关键词： gesture authentication depth camera one-class classification sparse autoencoder neural network incremental learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Model for Image Recognition

A Novel Deep Model for Image Recognition

引用

2014 IEEE 5th International Conference on Software Engineering and Service Science

作者： Ming Zhu Yan Wu College of Electronics & Information Engineering University of Tongji

In this paper we propose a hybrid deep network for image *** we use the sparse autoencoder(SAE) which is a method to extract high-level feature representations of data in an unsupervised way,without any manual feature engineering,and then we perform the classification using the deep belief networks(DBNs),which consist of restricted Boltzmann machine(RBM).Finally,we implement some comparative experiments on image datasets,and the results show that our methods achieved better performance when compared with neural network and other deep learning techniques such as DBNs.

关键词： deep belief network sparse autoencoder image recognition

来源：评论

学校读者我要写书评

暂无评论

SAR Automatic Target Recognition Based on a Visual Cortical System

SAR Automatic Target Recognition Based on a Visual Cortical ...

引用

International Congress on Image and Signal Processing

作者： Jia Cheng Ni Yue Lei Xu Institute of Aeronautics and Astronautics Engineering Air Force Engineering University

ISBN: (纸本)9781479927654

Human Vision system is the most complex and accurate system. In order to extract better features about Synthetic Aperture Radar (SAR) targets, a SAR automatic target recognition (ATR) algorithm based on human visual cortical system is proposed. This algorithm contains three stages: (1) Image preprocessing (we use a Kuan filter to do the enhancement and an adaptive Intersecting Cortical Model (ICM) to do the segmentation) (2) Feature extraction using a sparse autoencoder. (3) Classification using a softmax regression classifier. Experiment result of MSTAR public data shows a better performance of recognition.

关键词： SAR Object Recognition Visual Cortex ICM sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

基于三维人脸建模的多视角人脸识别方法研究

基于三维人脸建模的多视角人脸识别方法研究

引用

作者：邢健飞杭州电子科技大学

学位级别：硕士

作为典型的模式识别任务，人脸识别有着巨大的实际应用价值与市场前景。理想环境下的人脸识别已经取得不俗成绩，然而，当所处环境变化（如姿态变换、夸张表情、阴阳脸、分辨率较低）时，识别难度增加，效果也急剧变差。与此同时，现有... 详细信息

作为典型的模式识别任务，人脸识别有着巨大的实际应用价值与市场前景。理想环境下的人脸识别已经取得不俗成绩，然而，当所处环境变化（如姿态变换、夸张表情、阴阳脸、分辨率较低）时，识别难度增加，效果也急剧变差。与此同时，现有方法大多数无法实时（在线）完成人脸识别任务，这也限制了人脸识别技术的应用。本文在浙江省大学生科技成果推广项目(2013R407063)的赞助下，以人脸识别的背景及目的意义为出发点，考虑到人脸的三维结构，分析研究了基于三维人脸建模的多视角人脸识别方法，本文主要完成了以下几方面的研究工作：（1）人脸检测阶段：为了确保系统的稳定性与实时性，选择了基于AdaBoost的人脸检测算法并将所得的分类器打包成XML文件的形式，为以后的实时人脸识别系统的搭建打下了基础。（2）三维人脸建模方面：在比较几种基于图像的三维人脸建模方法后，选择了基于单张正面的照片的三维人脸建模方法，与常规方法相比，该方法的可行性与实用性高，方法可以无缝链接到人脸识别系统中。本文提出了一套基于Candide-3的三维人脸建模方法，具体分为两步：首先，使用改进的ASM（主动形状模型）算法对定位正面人脸的特征点进行定位并根据临近点插值法确定非特征点坐标；然后，在纹理贴图阶段，本文依据DMS样条函数，在Candide-3标准模型的基础上生成了含更多顶点的人脸模型，使得建立的模型真实感和连续性更好。最后，给出了根据所建三维人脸模型生成的多视角人脸图像。（3）在人脸图像特征提取阶段：本文提出了基于深度神经网络的人脸识别方法，本文的深度神经网络的训练分为两步：无监督阶段与有监督阶段。其中，在无监督阶段，使用sparse autoencoder在大规模人脸库LFW的基础上进行图像恢复以训练深度神经网络。与此同时，为探讨网络层数对于识别效果的影响，本文训练了多种多层数的神经网络，实验结果表明，识别率并非与网络层数正相关；有监督阶段，采用邻近元分析的方法，利用混合人脸库人脸的多样性(多姿态、多表情、多种光照)，有目的地提高网络对于人脸的理解能力，减小相同人脸间距离，增大不同人脸间距离。实验结果表明，较传统方法，本文提出的特征提取算法可提取人脸图像的深度特征，适用于人脸姿态、表情、光照变化较大的人脸识别任务中，对于人脸识别方法的探究是一次有益的尝试。（4）在实际的人脸识别过程中：提出了一种“搜索半径”的概念。首先将每张图像用二进制数据表示。在图像检索过程中，先计算出图像间的二进制数据间的汉明距离，然后按照汉明距离排序，在汉明距离较小的半径内，寻找与待识别图像欧式距离最小的图像，根据阈值，确定该图像是否是待识别个体。实验结果表明，本套识别方法所用识别时间极小，适合于对实时性要求较高的人脸识别任务。（5）最后，本文将所有的算法整合起来，利用OpenCV、OpenGL、Armadillo等库搭建了人脸实时识别系统，并演示了系统的具体操作。实验结果表明，本套人脸系统识别效果好，识别时间短，是人脸识别较为理想的方案。

关键词：人脸识别三维人脸建模 AdaBoost Candide-3 sparse autoencoder 邻近元分析

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：