检索结果-内蒙古大学图书馆

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Gu, Xue Meng, Ziyao Liang, Yanchun Xu, Dong Huang, Han Han, Xiaosong Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Zhuhai College of Jilin University Zhuhai519041 China Department of Electrical Engineering and Computer Science Informatics Institute and Christopher S. Bond Life Sciences Center University of Missouri ColumbiaMO65211 United States School of Software Engineering South China University of Technology GuangZhou510006 China

ISBN: (纸本)9789811534249

Although deep neural networks (DNNs) play important roles in many fields, the architecture design of DNNs can be challenging due to the difficulty of input data representation, the huge number of parameters and the complex layer relationships. To overcome the obstacles of architecture design, we developed a new method to generate the optimal structure of DNNs, named Evolutionary Strategy-based Architecture Evolution (ESAE), consisting of a bi-level representation and a probability distribution learning approach. The bi-level representation encodes architectures in the gene and parameter levels. The probability distribution learning approach ensures the efficient convergence of the architecture searching process. By using Fashion-MNIST and CIFAR-10, the effectiveness of the proposed ESAS is verified. The evolved DNNs, starting from a trivial initial architecture with one single convolutional layer, achieved the accuracies of 94.48% and 93.49% on Fashion-MNIST and CIFAR-10, respectively, and require remarkably less hardware costs in terms of GPUs and running time, compared with the existing state-of-the-art manual screwed architectures. © 2020, 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

A local density optimization method based on a graph convolutional network

引用

Frontiers of Information Technology & Electronic engineering 2020年第12期21卷 1795-1803页

作者： Hao WANG Li-yan DONG Tie-hu FAN Ming-hui SUN College of Computer Science and Technology Jilin UniversityChangchun 130012China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin UniversityChangchun 130012China College of Instrumentation&Electrical Engineering Jilin UniversityChangchun 130012China

Success has been obtained using a semi-supervised graph analysis method based on a graph convolutional network(GCN).However,GCN ignores some local information at each node in the graph,so that data preprocessing is incomplete and the model generated is not accurate ***,in the case of numerous unsupervised models based on graph embedding technology,local node information is *** this paper,we apply a local analysis method based on the similar neighbor hypothesis to a GCN,and propose a local density definition;we call this method *** LDGCN algorithm processes the input data of GCN in two methods,i.e.,the unbalanced and balanced ***,the optimized input data contains detailed local node information,and then the model generated is accurate after *** also introduce the implementation of the LDGCN algorithm through the principle of GCN,and use three mainstream datasets to verify the effectiveness of the LDGCN algorithm(i.e.,the Cora,Citeseer,and Pubmed datasets).Finally,we compare the performances of several mainstream graph analysis algorithms with that of the LDGCN *** results show that the LDGCN algorithm has better performance in node classification tasks.

关键词： Semi-supervised learning Graph convolutional network Graph embedding Local density

来源：评论

学校读者我要写书评

暂无评论

Crossed-Time Delay Neural Network for Speaker Recognition

arXiv

引用

arXiv 2020年

作者： Chen, Liang Liang, Yanchun Shi, Xiaohu Zhou, You Wu, Chunguo Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China Zhuhai Laboratory of Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education School of Computer Zhuhai College Jilin University Zhuhai519041 China

Time Delay Neural Network (TDNN) is a well-performing structure for deep neural network-based speaker recognition systems. In this paper we introduce a novel structure, named Crossed-Time Delay Neural Network (CTDNN) to enhance the performance of current TDNN for speaker recognition. Inspired by the multi-filters setting of convolution layers from convolution neural networks, we set multiple time delay units with different context size at the bottom layer and construct a multilayer parallel network. The proposed CTDNN gives significant improvements over original TDNN on both speaker verification and identification tasks. It outperforms in VoxCeleb1 dataset in verification experiment with a 2.6% absolute Equal Error Rate improvement. In few shots condition, CTDNN reaches 90.4% identification accuracy, which doubles the identification accuracy of original TDNN. We also compare the proposed CTDNN with another new variant of TDNN, Factorized-TDNN, which shows that our model has a 36% absolute identification accuracy improvement under few shots condition. Moreover, the proposed CTDNN can handle training with a larger batch more efficiently and hence, utilize calculation resources economically. The code of the new model is released at https://***/chenllliang/CTDNN. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Xdn: towards efficient inference of residual neural networks on cambricon chips 2nd

Xdn: towards efficient inference of residual neural networks...

引用

2nd International Symposium on Benchmarking, Measuring, and Optimization, Bench 2019

作者： Li, Guangli Wang, Xueying Ma, Xiu Liu, Lei Feng, Xiaobing State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China College of Computer Science and Technology Jilin University Changchun China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun China

ISBN: (纸本)9783030495558

In this paper, we present XDN, an optimization and inference engine for accelerating residual neural networks on Cambricon chips. We leverage a channel pruning method to compress the weights of ResNet-50. By exploring the optimization opportunities in computational graphs, we propose a layer fusion strategy, which dramatically decreases the number of scalar computation layers, such as Batch Normalization, Scale. Furthermore, we design an efficient implementation of XDN, including data preprocessing, hyper-parameter auto-tuning, etc. The experimental results show that the ResNet-50 model can achieve significant speedup without accuracy loss by using our XDN engine. © Springer Nature Switzerland AG 2020.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

TDCA: Improved Optimization Algorithm with Degree Distribution and Communication Traffic for the Deployment of Software Components Base on AUTOSAR Architecture

Research Square

引用

Research Square 2021年

作者： Zhang, Kunpeng Liu, Yanheng Zhang, Jindong Zhang, Guanhua Jin, Jingyi Li, Yunhao Tang, Fengmin College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation and Knowledge Engineering The Ministry of Education Jilin University Changchun China State Key Laboratory of Automobile Simulation and Control Jilin University Changchun China College of Mechanical Engineering Hebei University of Technology Tianjin300132 China China Automotive Technology and Research Center Tianjin300300 China

AUTOSAR (Automotive Open System Architecture), as an open, standardized framework for automotive electronic software development, has gradually become the standard followed by major automotive manufacturers and automotive electronic device suppliers. The electronic software system problem improves the development efficiency and portability of the system by reducing the development cost of automotive electronic software while ensuring the quality of products and services, which is beneficial for subsequent upgrades and updates of the system. In order to improve the reliability of the software component deployment algorithm based on AUTOSAR architecture, we proposed the TDCA algorithm. During the execution of the algorithm, communication volume and communication degree are introduced to improve the accuracy of the deployment plan by optimizing the bus load and ECU balancing. Algorithm comparison experiments show that comparing heuristic and linear optimization algorithms, the TDCA algorithm proposed in this paper has significant advantages in reducing bus load and ECU utilization. The algorithm can reduce the communication between cores and balance ECU load according to the constraints of AUTOSAR architecture. © 2021, CC BY.

关键词： Equalizers

来源：评论

学校读者我要写书评

暂无评论

Supervised topic models with weighted words:multi-label document classification

引用

Frontiers of Information Technology & Electronic engineering 2018年第4期19卷 513-523页

作者： Yue-peng ZOU Ji-hong OUYANG Xi-ming LI College of Computer Science and Technology Jilin University MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University

Supervised topic modeling algorithms have been successfully applied to multi-label document classification *** models include labeled latent Dirichlet allocation(L-LDA)and ***,these models neglect the class frequency information of words(i.e.,the number of classes where a word has occurred in the training data),which is significant for *** address this,we propose a method,namely the class frequency weight(CF-weight),to weight words by considering the class frequency *** CF-weight is based on the intuition that a word with higher(lower)class frequency will be less(more)*** this study,the CF-weight is used to improve L-LDA and dependency-LDA.A number of experiments have been conducted on real-world multi-label *** results demonstrate that CF-weight based algorithms are competitive with the existing supervised topic models.

关键词： Supervised topic model Multi-label classification Class frequency Labeled latent Dirichlet allocation (L-LDA) Dependency-LDA

来源：评论

学校读者我要写书评

暂无评论

Warburg Effects in Cancer and Normal Proliferating Cells:Two Tales of the Same Name

引用

Genomics, Proteomics & Bioinformatics 2019年第3期17卷 273-286页

作者： Huiyan Sun Liang Chen Sha Cao Yanchun Liang Ying Xu The China-Japan Union Hospital Jilin UniversityChangchun 130033China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and TechnologyJilin UniversityChangchun 130012China Computational Systems Biology Lab Department of Biochemistry and Molecular Biology and Institute of BioinformaticsUniversity of GeorgiaAthensGA 30602USA Faculty of Health Sciences University of MacaoTaipaMacao SAR 999078China Department of Biostatistics School of MedicineIndiana UniversityIndianapolisIN 46202USA Zhuhai Laboratory of MOE Key Laboratory of Symbolic Computation and Knowledge Engineering Zhuhai College of Jilin UniversityZhuhai 519041China

It has been observed that both cancer tissue cells and normal proliferating cells(NPCs)have the Warburg *** goal here is to demonstrate that they do this for different *** accomplish this,we have analyzed the transcriptomic data of over 7000 cancer and control tissues of 14 cancer types in TCGA and data of five NPC types in *** analyses reveal that NPCs accumulate large quantities of ATPs produced by the respiration process before starting the Warburg effect,to raise the intracellular pH from 6.8 to 7.2 and to prepare for cell division *** cell cycle starts,the cells start to rely on glycolysis for ATP generation followed by ATP hydrolysis and lactic acid release,to maintain the elevated intracellular pH as needed by cell division since together the three processes are pH *** cells go back to the normal respirationbased ATP production once the cell division phase *** comparison,cancer cells have reached their intracellular pH at 7.4 from top down as multiple acid-loading transporters are up-regulated and most acid-extruding ones except for lactic acid exporters are *** cells use continuous glycolysis for ATP production as way to acidify the intracellular space since the lactic acid secretion is decoupled from glycolysis-based ATP generation and is pH balanced by increased expressions of acid-loading ***-expression analyses suggest that lactic acid secretion is regulated by external,non-pH related ***,our data strongly suggest that the two cell types have the Warburg effect for very different reasons.

关键词： Cancer Warburg effect Fenton reaction Cell proliferation pH homeostasis

来源：评论

学校读者我要写书评

暂无评论

IInfoGAN: Improved Information Maximizing Generative Adversarial Networks

IInfoGAN: Improved Information Maximizing Generative Adversa...

引用

International Conference on Mechanical, Control and Computer engineering (ICMCCE)

作者： Yan Wang Pujia Wang Boyang Sun Kai He Lan Huang School of Artificial Intelligence Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Ministry of Education Changchun China

Generative Adversarial Networks (GANs) have achieved huge success in some unsupervised learning fields. There is no doubt that clustering takes a lot of weight in unsupervised algorithm. And in this paper, we raise the Improved Information Maximizing Generative Adversarial Networks (IInfoGAN) algorithm for learning discriminative classifiers from unlabeled data. The basis of our method is an math function that contains the Mutual Information (MI) and Cross Entropy of the observed examples and their predicted classification category distribution, thus enhancing the robustness of the classifier to adversarial generative models. Experiments show that the interpretable representation learned by IInfoGAN is competitive with the representation learned by existing unsupervised methods.

关键词： Training Time series analysis Clustering algorithms Predictive models Generative adversarial networks Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

BAENET: A Brain Age Estimation Network with 3D Skipping and Outlier Constraint Loss

BAENET: A Brain Age Estimation Network with 3D Skipping and ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Taiping Qu Yangming Yue Qirui Zhang Cheng Wang Zhiqiang Zhang Guangming Lu Wei Du Xiuli Li Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China Deepwise AI Lab Beijing China Jinling Hospital Medical School of Nanjing University Nanjing Jiangsu China

ISBN: (数字)9781538693308

ISBN: (纸本)9781538693315

The potential pattern changes in brain micro-structure can be used for the brain development assessment in children and adolescents by MRI scans. In this paper, we propose a highly accurate and efficient end-to-end brain age estimation network (BAENET) on T1-weighted MRI images. On the network, 3D skipping and outlier constraint loss are designed to accommodate deeper network and increase the robustness. Besides, we incorporate the neuroimaging domain knowledge into stratified sampling for better generalization ability for datasets with different age distributions, and gender learning for more gender-specific features during modeling. We verify the effectiveness of the proposed method on the public ABIDE2 and ADHD200 benchmark, consisting of 382 and 378 normal children scans respectively. Our BAENET achieves MAE of 1.11 and 1.16, significantly outperforming the best reported methods by 5.1 % and 9.4%.

关键词： Three-dimensional displays Brain modeling Estimation Solid modeling Feature extraction Magnetic resonance imaging Task analysis

来源：评论

学校读者我要写书评

暂无评论

computational Prediction of Human Body-Fluid Protein

Computational Prediction of Human Body-Fluid Protein

引用

IEEE International Conference on Bioinformatics and Biomedicine

作者： Dan Shao Xueteng Cui Lan Huang Kai He Yan Wang Yao Wang Key laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University College of Computer Science and Technology Changchun University Key laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University

ISBN: (纸本)9781728118680

Research on body fluid proteomes has led to the discoveries of context-dependent proteomics profiles and numerous novel disease biomarkers. Common challenges remain with current proteomics technologies about how to effectively handle the large variety of protein modifications in those fluids. To this end, computational efforts have shown early successes in identifying biomarker proteins in specific human diseases. In this article, we first reviewed published computational methods on this topic and then presented a new database system and a novel deep learning-based method for predicting body-fluid proteins in 16 types of human fluids. The results show that our new system outperforms existing methods and provides a highly promising tool to facilitate clinical proteomic discovery.

关键词： machine learning protein prediction body-fluid proteome deep learning Machine Learning Database systems Artificial Intelligence proteomics protein modifications Fluid Human Body maladjustment Learning-based method Biological Markers Body Fluids

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：