检索结果-内蒙古大学图书馆

EEEA-Net: An Early Exit evolutionary Neural Architecture Search

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2021年 104卷 104397-104397页

作者： Termritthikun, Chakkrit Jamtsho, Yeshi Ieamsaard, Jirarat Muneesawang, Paisarn Lee, Ivan Univ South Australia STEM Adelaide SA 5095 Australia Naresuan Univ Fac Engn Dept Elect & Comp Engn Phitsanulok 65000 Thailand Royal Univ Bhutan Coll Sci & Technol Phuentsholing 21101 Bhutan

The goals of this research were to search for Convolutional Neural Network (CNN) architectures, suitable for an on-device processor with limited computing resources, performing at substantially lower Network Architecture Search (NAS) costs. A new algorithm entitled an Early Exit Population Initialisation (EE-PI) for evolutionary Algorithm (EA) was developed to achieve both goals. The EE-PI reduces the total number of parameters in the search process by filtering the models with fewer parameters than the maximum threshold. It will look for a new model to replace those models with parameters more than the threshold. Thereby, reducing the number of parameters, memory usage for model storage and processing time while maintaining the same performance or accuracy. The search time was reduced to 0.52 GPU day. This is a huge and significant achievement compared to the NAS of 4 GPU days achieved using NSGA-Net, 3,150 GPU days by the AmoebaNet model, and the 2,000 GPU days by the NASNet model. As well, Early Exit evolutionary Algorithm networks (EEEA-Nets) yield network architectures with minimal error and computational cost suitable for a given dataset as a class of network algorithms. Using EEEA-Net on CIFAR-10, CIFAR-100, and ImageNet datasets, our experiments showed that EEEA-Net achieved the lowest error rate among state-of-the-art NAS models, with 2.46% for CIFAR-10, 15.02% for CIFAR-100, and 23.8% for ImageNet dataset. Further, we implemented this image recognition architecture for other tasks, such as object detection, semantic segmentation, and keypoint detection tasks, and, in our experiments, EEEA-Net-C2 outperformed MobileNet-V3 on all of these various tasks. (The algorithm code is available at https://***/chakkritte/EEEA-Net).

关键词： Deep learning Neural Architecture Search multi-objective evolutionary algorithms Image classification

来源：评论

学校读者我要写书评

暂无评论

multi-objective evolutionary Neural Network to Predict Graduation Success at the United States Military Academy

引用

Procedia Computer Science 2018年 140卷 196-205页

作者： Gene Lesinski Steven Corns United States Military Academy West Point NY 10996 USA Missouri University of Science and Technology Rolla MO 10996 USA

This paper presents an evolutionary neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A pareto-based, multi-objective evolutionary algorithm utilizing the Strength Pareto evolutionary Algorithm (SPEA2) fitness evaluation scheme simultaneously evolves connection weights and identifies the neural network topology using network complexity and classification accuracy as objective functions. A combined vector-matrix representation scheme and differential evolution recombination operators are employed. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. The inputs to the evolutionary neural network model are used to classify students as: graduates, late graduates, or non-graduates. Results of the hybrid method show higher mean classification rates (88%) than the current methodology (80%) with a potential savings of $130M. Additionally, the proposed method is more efficient in that a less complex neural network topology is identified by the algorithm.

关键词： evolutionary algorithms, Neural network multi-objective evolutionary algorithms enrollment management student retention

来源：评论

学校读者我要写书评

暂无评论

OPLA-Tool v2.0: a Tool for Product Line Architecture Design Optimization 20

OPLA-Tool v2.0: a Tool for Product Line Architecture Design ...

引用

34th Brazilian Symposium on Software Engineering (SBES)

作者： Freire, Willian Marques Massago, Mamoru Zavadski, Arthur Cattaneo Malachini Miotto Amaral, Aline Maria Colanzi, Thelma Elita Univ Estadual Maringa Maringa Parana Brazil

ISBN: (纸本)9781450387538

The multi-objective Optimization Approach for Product Line Architecture Design (MOA4PLA) is the seminal approach that successfully optimizes Product Line Architecture (PLA) design using search algorithms. The tool named OPLA-Tool was developed in order to automate the use of MOA4PLA. Over time, the customization of the tool to suit the needs of new research and application scenarios led to several problems. The main problems identified in the original version of OPLA-Tool are environment configuration, maintainability and usability problems, and PLA design modeling and visualization. Such problems motivated the development of a new version of this tool: OPLA-Tool v2.0, presented in this work. In this version, those problems were solved by the source code refactoring, migration to a web-based graphical user interface (GUI) and inclusion of a new support tool for PLA modeling and visualization. Furthermore, OPLA-Tool v2.0 has new functionalities, such as new objective functions, new search operators, intelligent interaction with users during the optimization process, multi-user authentication and simultaneous execution of several experiments to PLA optimization. Such a new version of OPLA-Tool is an important achievement to PLA design optimization as it provides an easier and more complete way to automate this task.

关键词： Software product line product line architecture multi-objective evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Outlook on Feature Selection as a multi-objective Problem 1

引用

14th Biennial International Conference on Artificial Evolution (EA)

作者： Barbiero, Pietro Lutton, Evelyne Squillero, Giovanni Tonda, Alberto Politecn Torino Turin Italy Univ Paris Saclay AgroParisTech INRA UMR 782 Thiverval Grignon France

ISBN: (数字)9783030457150

ISBN: (纸本)9783030457150

Feature selection is the process of choosing, or removing, features to obtain the most informative feature subset of minimal size. Such subsets are used to improve performance of machine learning algorithms and enable human understanding of the results. Approaches to feature selection in literature exploit several optimization algorithms. multi-objective methods also have been proposed, minimizing at the same time the number of features and the error. While most approaches assess error resorting to the average of a stochastic K-fold cross-validation, comparing averages might be misleading. In this paper, we show how feature subsets with different average error might in fact be non-separable when compared using a statistical test. Following this idea, clusters of nonseparable optimal feature subsets are identified. The performance in feature selection can thus be evaluated by verifying how many of these optimal feature subsets an algorithm is able to identify. We thus propose a multi-objective optimization approach to feature selection, EvoFS, with the objectives to i. minimize feature subset size, ii. minimize test error on a 10-fold cross-validation using a specific classifier, iii. maximize the analysis of variance value of the lowest-performing feature in the set. Experiments on classification datasets whose feature subsets can be exhaustively evaluated show that our approach is able to always find the best feature subsets. Further experiments on a high-dimensional classification dataset, that cannot be exhaustively analyzed, show that our approach is able to find more optimal feature subsets than state-of-the-art feature selection algorithms.

关键词： Feature selection Machine learning multi-objective optimization evolutionary algorithms multi-objective evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

multimodal multi-objective Optimization Using A Density-based One-by-One Update Strategy

Multimodal Multi-objective Optimization Using A Density-base...

引用

IEEE Congress on evolutionary Computation (IEEE CEC)

作者： Shi, Ruizhi Lin, Wu Lin, Qiuzhen Zhu, Zexuan Chen, Jianyong Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen Guangdong Peoples R China

ISBN: (纸本)9781728121536

For real-world optimization problems, a uniformly and widely distributed Pareto optimal set (PS) in the decision space can provide more choices for decision makers. However, most of multi-objective evolutionary algorithms (MOEAs) only consider convergence and diversity in the objective space, which rarely pay attention to diversity in the decision space. Especially for multimodal multi-objective optimization problems (MMOPs), there may exist multiple distinct PSs corresponding to the same Pareto front (PF). Thus, we propose a novel multimodal multi-objective evolutionary algorithm using a density-based one-by-one update strategy in this paper, which considers diversity in both the objective and decision spaces. In the proposed algorithm, once an offspring is generated during evolution, the most crowded subregion with the largest niche count in the objective space has to be identified again, helpful to maintain diversity in the objective space. Furthermore, the harmonic average distance approach is used to estimate the global density of solutions in the decision space, trying to maintain the population's diversity in the decision space. Our proposed algorithm is compared with several state-of-the-art algorithms on MMOPs. The experimental results demonstrate that our algorithm is capable of preserving promising solutions with even distribution in both of decision space and objective space and also shows the superiority on solving the adopted MMOPs.

关键词： multi-objective evolutionary algorithms multimodal multi-objective optimization global density harmonic average distance

来源：评论

学校读者我要写书评

暂无评论

Marginalization in Mexico: An Application of the ELECTRE III-MOEA Methodology 8

Marginalization in Mexico: An Application of the ELECTRE III...

引用

8th International Conference on evolutionary multi-Criterion Optimization (EMO)

作者： Solano Noriegal, Jesus Jaime Leyva Lopez, Juan Carlos Gastelum Chavira, Diego Alonso Univ Autonoma Ciudad Juarez Juarez Chihuahua Mexico Univ Occidente Culiacan Sinaloa Mexico Univ Autonoma Sinaloa Culiacan Sinaloa Mexico

ISBN: (纸本)9783319158921;9783319158914

In this paper, a multi-criteria approach for ranking the Municipalities of the States of Mexico by their levels of marginalization is proposed, and the case for the State of Jalisco is presented. The approach uses the ELECTRE III method to construct a medium-sized valued outranking relation and then employs a new multi-objective evolutionary algorithm (MOEA) based on non-dominated sorting genetic algorithm II (NSGA-II) to exploit the relation to obtain a recommendation. The results of this application can be useful for policy-makers, planners, academics, investors, and business leaders. This study also contributes to an important, yet relatively new, body of application-based literature that investigates multi-criteria approaches to decision making that use fuzzy theory and evolutionary multi-objective optimization methods. A comparison of the ranking obtained with the proposed methodology and the stratifications created by the National Population Council of Mexico shows that the methodology presented consistent and reliable results for this problem.

关键词： multi-criteria decision analysis Municipal marginalization Ranking problem ELECTRE III multi-objective evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Polymer A Model-driven Approach for Simpler, Safer, and Evolutive multi-objective Optimization Development 3

Polymer <i>A Model</i>-<i>driven Approach for Simpler</i>, <...

引用

3rd International Conference on Model-Driven Engineering and Software Development (MODELSWARD)

作者： Moawad, Assaad Hartmann, Thomas Fouquet, Francois Nain, Gregory Klein, Jacques Bourcier, Johann Univ Luxembourg Interdisciplinary Ctr Secur Reliabil & Trust Luxembourg Luxembourg Univ Rennes 1 IRISA INRIA Rennes France

ISBN: (纸本)9789897581366

multi-objective evolutionary algorithms (MOEAs) have been successfully used to optimize various domains such as finance, science, engineering, logistics and software engineering. Nevertheless, MOEAs are still very complex to apply and require detailed knowledge about problem encoding and mutation operators to obtain an effective implementation. Software engineering paradigms such as domain-driven design aim to tackle this complexity by allowing domain experts to focus on domain logic over technical details. Similarly, in order to handle MOEA complexity, we propose an approach, using model-driven software engineering (MDE) techniques, to define fitness functions and mutation operators without MOEA encoding knowledge. Integrated into an open source modelling framework, our approach can significantly simplify development and maintenance of multi-objective optimizations. By leveraging modeling methods, our approach allows reusable optimizations and seamlessly connects MOEA and MDE paradigms. We evaluate our approach on a cloud case study and show its suitability in terms of i) complexity to implement an MOO problem, ii) complexity to adapt (maintain) this implementation caused by changes in the domain model and/or optimization goals, and iii) show that the efficiency and effectiveness of our approach remains comparable to ad-hoc implementations.

关键词： multi-objective evolutionary algorithms Optimization Genetic algorithms Model-driven Engineering

来源：评论

学校读者我要写书评

暂无评论

Dynamic Task Graph Scheduling on multicore Processors for Performance, Energy, and Temperature Optimization

Dynamic Task Graph Scheduling on Multicore Processors for Pe...

引用

International Green Computing Conference (IGCC)

作者： Sheikh, Hafiz Fahad Ahmad, Ishfaq Univ Texas Arlington Dept Comp Sci & Engn Arlington TX 76019 USA

ISBN: (纸本)9781479906239

Despite significant advancements in multicore processor technology for reducing the chip-level energy consumption, higher levels of power dissipation resulting in thermal implications and cooling costs remain as unsolved problems. Although several scheduling methods of controlling and managing the power dissipation and temperature exist, most schemes are static that are unable to adjust to the dynamic program and system changes. This paper presents dynamic method for voltage-scaling based task scheduling for simultaneous optimization of performance, energy, and temperature (PET quantities) under dynamically varying task and system conditions. Our method generates an initial set of Pareto optimal solutions utilizing a multi-objective evolutionary algorithm (MOEA) called SPEA-II (Strength Pareto evolutionary Algorithm). This set of solutions is dynamically evolved with time to minimize the deviation of PET quantities from the Pareto optimal values. We carried out extensive evaluations using several task graph benchmarks based on the data obtained from a real multicore machine. The results indicate that the proposed dynamic re-optimization achieves up to 8% improvement in PET quantities as compared to the statically selected schedule.

关键词： dynamic task scheduling dynamic thermal management multi-objective evolutionary algorithms multicore system dynamic voltage and frequency scaling

来源：评论

学校读者我要写书评

暂无评论

RCS Reduction For UAV Array

RCS Reduction For UAV Array

引用

Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC)

作者： Zhou, Lei Zhou, Haosu Wang, Yizhao Liu, Beichen Lv, Zhenbin Tang, Qi Shanghai Spaceflight Elect & Commun Equipment Res Sci & Technol Near Surface Detect Lab Shanghai Peoples R China Shanghai Spaceflight Elect & Commun Equipment Res Shanghai Peoples R China Nanjing Univ Sci & Technol Nanjing Peoples R China Sci & Technol Near Suiface Detect Lab Wuxi Jiangsu Peoples R China

ISBN: (纸本)9781665432436

It is difficult to achieve the effect of raid target because of the large Radar Cross Section (RCS) of Unmanned Aerial Vehicle (UAV) group when carrying out military missions. This paper proposes a method to reduce RCS of UAV linear array. Based on the principle of array scattering pattern synthesis, this paper calculates the RCS of a linear array UAV group and optimizes the posture of the UAV through a multi-objective evolutionary algorithm so that the RCS of the UAV group is significantly reduced within the viewing angle. The simulation results show that the reasonable arrangement of UAVs significantly reduces the RCS of the group within the specified viewing angle range.

关键词： scattering pattern function multi-objective evolutionary algorithms Radar Cross Section (RCS)

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL BUFFER ALLOCATION FOR SEMI-SYNCHRONIZED AUTOMOTIVE ASSEMBLY LINES USING SIMULATION-BASED multi-objective OPTIMIZATION

OPTIMAL BUFFER ALLOCATION FOR SEMI-SYNCHRONIZED AUTOMOTIVE A...

引用

9th International Industrial Simulation Conference

作者： Bernedixen, Jacob Ng, Amos H. C. Univ Skovde Virtual Syst Res Ctr SE-54128 Skovde Sweden

ISBN: (纸本)9789077381632

A practical question in industry in designing or re-designing a production system is: how small can intermediate buffers be to ensure the desired production rate? This topic is usually called optimal buffer allocation as the goal is to allocate the minimum buffer capacities to optimize the performance of the line. This paper presents a case study of using simulation based evolutionary multi-objective optimization to determine the optimal buffer capacities and positions in the re-configuration of a real-world truck axle assembly line in an automobile manufacturer. The case study has not only revealed the applicability of the methodology in seeking optimal configurations in a truly multi-objective context, it also illustrates how additional important knowledge was gained by analyzing the optimization results in the objective space.

关键词： Synchronized Assembly Optimal Buffer Allocation Simulation-based Optimization multi-objective evolutionary algorithms

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：