检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2022年第5期3卷 722-737页

作者： Huang, Shihua He, Cheng Cheng, Ran Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China

Despite significant advances in image-to-image (I2I) translation with generative adversarial networks (GANs), it remains challenging to effectively translate an image to a set of diverse images in multiple target domains using a pair of generator and discriminator. Existing multimodal I2I translation methods adopt multiple domain-specific content encoders for different domains, where each domain-specific content encoder is trained with images from the same domain only. Nevertheless, we argue that the content (domain-invariance) features should be learned from images among all of the domains. Consequently, each domain-specific content encoder of existing schemes fails to extract the domain-invariant features efficiently. To address this issue, we present a flexible and general SoloGAN model for efficient multimodal I2I translation among multiple domains with unpaired data. In contrast to existing methods, the SoloGAN algorithm uses a single projection discriminator with an additional auxiliary classifier and shares the encoder and generator for all domains. As such, the SoloGAN model can be trained effectively with images from all domains so that the domain-invariance content representation can be efficiently extracted. Qualitative and quantitative results over a wide range of datasets against several counterparts and variants of the SoloGAN model demonstrate the merits of the method, especially for challenging I2I translation tasks, i.e., tasks that involve extreme shape variations or need to keep the complex backgrounds unchanged after translations. Furthermore, we demonstrate the contribution of each component using ablation studies. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-objective evolutionary optimization for hardware-aware neural network pruning

引用

Fundamental Research 2024年第4期4卷 941-950页

作者： Wenjing Hong Guiying Li Shengcai Liu Peng Yang Ke Tang Guangdong Provincial Key Laboratory of Brain-Inspired Inteligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Research Institute of Trustworthy Autonomous Systems Southern University of Science and TechnologyShenzhen 518055China Department of Statistics and Data Science Southern University of Science and TechnologyShenzhen 518055China

Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics,and as new types of hardware become increasingly available,hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention,Both network accuracy and hardware efficiency(latency,memory consumption,etc.)are critical objectives to the success of network pruning,but the conflict between the multiple objectives makes it impossible to find a single optimal *** studies mostly convert the hardware-aware network pruning to optimization problems with a single *** this paper,we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms(MOEAs).Specifically,we formulate the problem as a multi-objective optimization problem,and propose a novel memetic MOEA,namely HAMP,that combines an efficient portfoliobased selection and a surrogate-assisted local search,to solve *** studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.

关键词： Multi-objective optimization Evolutionary algorithm Neural network pruning Hardware-awaremachine learning Hardware efficiency

来源：评论

学校读者我要写书评

暂无评论

A Concept-Based Local Interpretable Model-Agnostic Explanation Approach for Deep Neural Networks in Image Classification 13th

A Concept-Based Local Interpretable Model-Agnostic Explanati...

引用

13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024

作者： Tan, Lidan Huang, Changwu Yao, Xin Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9783031579189

A well-recognized and widely-used explainable artificial intelligence (XAI) method is Local Interpretable Model-agnostic Explanations (LIME), which offers instance-level interpretation by generating new data around the instance and training a locally interpretable linear model. However, when using LIME to explain the image classification model, it generates interpretations at the level of super-pixel representation. This does not assure comprehensibility to humans due to the lack of semantic information in super-pixels. To enhance the intelligibility of LIME, we propose an advanced version of LIME, termed Concept-based Local Interpretable Model-agnostic Explanations (ConceptLIME). In ConceptLIME, the explanations are formulated in terms of human-understandable concepts as opposed to the semantically deficient super-pixels, thereby augmenting the comprehensibility of the original LIME method. Comparative experiments have been conducted between ConceptLIME and LIME to validate the effectiveness of ConceptLIME. The experimental results indicate that ConceptLIME outperforms LIME regarding predictive performance on both the perturbation dataset and the explained instances. Moreover, the fidelity of the explanations generated by ConceptLIME surpasses that produced by LIME. The interpretations provided by ConceptLIME are more intelligible and intuitive than LIME’s explanations. Consequently, our proposed ConceptLIME exhibits superior properties, including predictive performance, fidelity, and comprehensibility, when compared with LIME. © IFIP International Federation for Information Processing 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Ensemble R2-based Hypervolume Contribution Approximation

Ensemble R2-based Hypervolume Contribution Approximation

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Wu, Guotong Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

The hypervolume-based multi-objective evolutionary algorithms (HV-MOEAs) have proven to be highly effective in solving multi-objective optimization problems. However, the computation time of the hypervolume calculation increases significantly as the number of objectives increases. To address this issue, an R2-based hypervolume contribution approximation (R2-HVC) method was proposed. Nevertheless, the original R2-HVC generates a large number of vectors and computes the HVC only once. In this study, we propose an ensemble method based on the R2-HVC method. By using a small number of vectors for repetitive computation and majority voting, the ensemble method can reduce the probability of making incorrect choices. Experimental results show that the proposed method can improve the approximation accuracy while maintaining a similar computation time to the original R2-HVC method. © 2023 IEEE.

关键词： Ensemble Method Hypervolume Contribution Majority Voting Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Normalization in R2-Based Hypervolume and Hypervolume Contribution Approximation

Normalization in R2-Based Hypervolume and Hypervolume Contri...

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Wu, Guotong Shu, Tianye Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

In this paper, we examine the effect of normalization in R2-based hypervolume and hypervolume contribution approximation. The fact is that the region with different scales on objective space brings approximation bias. The basic idea of normalization is to perform a coordinate transformation to make the shape of the approximated region more regular, and then transform it to obtain the final value according to the property of hypervolume and hypervolume contribution. The performance of normalization is evaluated on different datasets by comparing it with the original R2-based method. We use two different metrics to evaluate hypervolume and hypervolume contribution separately, and the results indicate that normalization does exactly improve the approximation accuracy and outperforms the original R2-based method. © 2023 IEEE.

关键词： Hypervolume Normalization ─Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

MINERVA: Secure Collaborative Machine Tool Data Utilization Leveraging Confidentiality-Protecting Technologies

MINERVA: Secure Collaborative Machine Tool Data Utilization ...

引用

Open Identity Summit 2024

作者： Ludwig, Andy Heinl, Michael P. Giehl, Alexander Fraunhofer AISEC Department Product Protection and Industrial Security Garching bei München Germany Technical University of Munich TUM School of Computation Information and Technology Department of Computer Engineering IT Security Germany

ISBN: (纸本)9783885797449

The digitization of shop floors opens up opportunities for innovative applications and business models due to the vast amount of generated data. However, a lot of this potential is currently not utilized because companies consider the risk of data sharing as too high compared to the corresponding benefit. Focusing on the machine tool sector, the research project MINERVA addresses these concerns by experimentally repurposing privacy-enhancing technologies as confidentiality-protecting technologies and applying them to the use case of condition monitoring to protect intellectual property and other information deemed critical by machine tool operators. Thereby, MINERVA’s goal is to reduce the risk of data sharing and support the establishment of data-driven business models in the machine tool sector in the long term. © 2024 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Analysis of Partition Methods for Dominated Solution Removal from Large Solution Sets

Analysis of Partition Methods for Dominated Solution Removal...

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Shu, Tianye Nan, Yang Shang, Ke Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

In evolutionary multi-objective optimization (EMO), one important issue is to efficiently remove dominated solutions from a large number of solutions examined by an EMO algorithm. An efficient approach to remove dominated solutions from a large solution set is to partition it into small subsets. Dominated solutions are removed from each subset independently. This partition method is fast but cannot guarantee to remove all dominated solutions. To further remove remaining dominated solutions, a simple idea is to iteratively perform this approach. In this paper, we first examine three partition methods (random, objective value-based and cosine similarity-based methods) and their iterative versions through computational experiments on artificial test problems (DTLZ and WFG) and real-world problems. Our results show that the choice of an appropriate partition method is problem dependent. This observation motivates us to use a hybrid approach where different partition methods are used in an iterative manner. The results show that all dominated solutions are removed by the hybrid approach in most cases. Then, we examine the effects of the following factors on the computation time and the removal performance: the number of objectives, the shape of the Pareto front, and the number of subsets in each partition method. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Hypervolume Optimal μ-Distributions on Complex Pareto Fronts

Empirical Hypervolume Optimal μ-Distributions on Complex Pa...

引用

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Shang, Ke Shu, Tianye Wu, Guotong Nan, Yang Pang, Lie Meng Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9781665430654

Hypervolume optimal μ-distribution is the distribution of μ solutions maximizing the hypervolume indicator of μ solutions on a specific Pareto front. Most studies have focused on simple Pareto fronts such as triangular and inverted triangular Pareto fronts. There is almost no study which focuses on complex Pareto fronts such as disconnected and partially degenerate Pareto fronts. However, most real-world multi-objective optimization problems have such a complex Pareto front. Thus, it is of great practical significance to study the hypervolume optimal μ-distribution on the complex Pareto fronts. In this paper, we study this issue by empirically showing the hypervolume optimal μ-distributions on the Pareto fronts of some representative artificial and real-world test problems. Our results show that, in general, maximizing the hypervolume indicator does not lead to uniformly distributed solution sets on the complex Pareto fronts. We also give some suggestions related to the use of the hypervolume indicator for performance evaluation of evolutionary multi-objective optimization algorithms. © 2023 IEEE.

关键词： complex Pareto front Hypervolume multi-objective optimization optimal μ-distribution

来源：评论

学校读者我要写书评

暂无评论

How to Find a Large Solution Set to Cover the Entire Pareto Front in Evolutionary Multi-Objective Optimization

How to Find a Large Solution Set to Cover the Entire Pareto ...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Pang, Lie Meng Nan, Yang Ishibuchi, Hisao Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9798350337020

Recently, it has been pointed out in many studies that the performance of evolutionary multi-objective optimization (EMO) algorithms can be improved by selecting solutions from all examined solutions stored in an unbounded external archive. This is because in general the final population is not the best subset of the examined solutions. To obtain a good final solution set in such a solution selection framework, subset selection from a large candidate set (i.e., all examined solutions) has been studied. However, since good subsets cannot be obtained from poor candidate sets, a more important issue is how to find a good candidate set, which is the focus of this paper. In this paper, we first visually demonstrate that the entire Pareto front is not covered by the examined solutions through computational experiments using MOEA/D, NSGA-III and SMS-EMOA on DTLZ test problems. That is, the examined solution set stored in the unbounded archive has some large holes (i.e., some uncovered area of the Pareto front). Next, to evaluate the quality of the examined solution set (i.e., to measure the size of the largest hole), we propose the use of a variant of the inverted generational distance (IGD) indicator. Then, we propose a simple modification of EMO algorithms to improve the quality of the examined solution set. Finally, we demonstrate the effectiveness of the proposed modification through computational experiments. © 2023 IEEE.

关键词： Evolutionary multi-objective optimization Pareto front solution selection framework unbounded external archive

来源：评论

学校读者我要写书评

暂无评论

JL-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection 30

JL-Hate: An Annotated Dataset for Joint Learning of Hate Spe...

引用

Joint 30th International Conference on computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Buyukdemirci, Kaan Kucukkaya, Izzet Emre Olmez, Eren Toraman, Cagri Department of Electrical and Electronical Engineering Bilkent University Ankara Turkey School of Computation Information and Technology Technical University of Munich Munich Germany Department of Computer Engineering Middle East Technical University Ankara Turkey

ISBN: (纸本)9782493814104

The detection of hate speech is a subject extensively explored by researchers, and machine learning algorithms play a crucial role in this domain. The existing resources mostly focus on text sequence classification for the task of hate speech detection. However, the target of hateful content is another dimension that has not been studied in details due to the lack of data resources. In this study, we address this gap by introducing a novel tweet dataset for the task of joint learning of hate speech detection and target detection, called JL-Hate, for the tasks of sequential text classification and token classification, respectively. The JL-Hate dataset consists of 1,530 tweets divided equally in English and Turkish languages. Leveraging this dataset, we conduct a series of benchmark experiments. We utilize a joint learning model to concurrently perform sequence and token classification tasks on our data. Our experimental results demonstrate consistent performance with the prevalent studies, both in sequence and token classification tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Classification (of information)

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：