检索结果-内蒙古大学图书馆

Multi-objective optimization for reducing feature maps redundancy in CNNs

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第31期83卷 75671-75688页

作者： Boufssasse, Ali Hssayni, El houssaine Joudar, Nour-Eddine Ettaouil, Mohamed Sidi Mohamed Ben Abdellah Univ FST Fez Dept Math Fes Morocco Mohammed V Univ Rabat ENSIAS Rabat Morocco

Nowadays, Convolutional neural networks (CNNs) have achieved relevant results on several data sciences-related tasks, such as image processing and pattern recognition. However, CNNs contain an immense number of parameters which often leads to a huge redundancy, overfitting, and a significant amount of memory. In this paper, we aim to present a multi-objective optimization model for kernels redundancy reduction in convolutional neural networks. In fact, the suggested approach, named MOFM-CNN, allows to minimize redundant feature maps using a set of decision control variables. MOFM-CNN is composed of two objectives where in the first one, the decision variables are technically introduced in the cross-entropy function in order to evaluate the impact of each feature map on the CNNs training. In the second one, the control parameters are used to calculate the proportion of active feature maps, that is related to the complexity of the model. The resultant problem is manipulated and solved using non dominated sorting genetic algorithm (NSGA-II). The performance of our proposal is demonstrated visually and numerically for both classification and features maps optimization.

关键词： muli-objective optimization Pareto front NSGA-II Convolutional neural networks Feature map Image classification

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective optimization Model for Redundancy Reduction in Convolutional Neural Networks

引用

NEURAL PROCESSING LETTERS 2023年第7期55卷 9721-9741页

作者： Boufssasse, Ali Hssayni, El Houssaine Joudar, Nour-Eddine Ettaouil, Mohamed Sidi Mohamed Ben Abdellah Univ Dept Math FST Fez Fes Morocco Mohammed V Univ Rabat ENSIAS Rabat Morocco Mohammed V Univ Rabat ENSAM Rabat Morocco

Until now, convolutional neural networks (CNNs) still among the powerful and robust deep neural networks that proved its efficiency through several real applications. However, their functioning requires a large number of parameters which in turn lead to some undesired effects such as the overparametrization, overfitting and the high consumption of computational resources. To deal effectively with these issues, we propose in this paper a new multi-objective optimization model for redundancy reduction in CNNs. The suggested model named MoRR-CNN allows to eliminate the unwanted parameters (kernels and weights) as well as to speeding up the CNN evaluation process. It consists of two objectives, the first one is related to the training task where the solution is the optimal parameters. These parameters are combined with a set of decision variables that controlling their contribution in the training process, making at the end a redundancy-related objective function. Both of the objectives are optimized using the non dominated sorting genetic algorithm NSGA-II. The robustness of MoRR-CNN has been demonstrated through different experimentation applied on three benchmark datasets including MNIST, Fashion-MNIST and CIFAR and using three of the most known CNNs such as VGG-19, Net-in-Net and VGG-16.

关键词： muli-objective optimization Pareto front NSGA-II Convolutional neural networks Redundancy reduction Image classification

来源：评论

学校读者我要写书评

暂无评论

A New Multi-objective optimization Model for Optimal Configuration of CNNs 4th

A New Multi-objective Optimization Model for Optimal Configu...

引用

4th International Conference on Digital Technologies and Applications (ICDTA)

作者： Boufssasse, Ali Hssayni, El Houssaine Joudar, Nour-Eddine Ettaouil, Mohamed Sidi Mohamed Ben Abdellah Univ Dept Math FST Fez Fes Morocco Mohammed V Univ Rabat ENSIAS Rabat Morocco

ISBN: (纸本)9783031686528;9783031686535

In recent years, convolutional neural networks (CNNs) are compute-intensive learning models with growing applicability in a variety of real-world problems. However, determining an optimal CNN architecture is still unclear and needs mathematical development. Furthermore, most current CNN models are primarily crafted in a specific manner. This study introduces a novel multi-objective optimization model to find optimal hyperparameters related to CNN architecture. Our proposal simultaneously minimizes both cross-entropy loss and a related CNN complexity function. This model enables the fine control of each neuron's contribution within the CNN's fully connected layers through a set of associated decision variables. To solve the resulting model, we opt for the evolutionary multi-objective algorithm (NSGA-II). Extensive experiment on three benchmark datasets MNIST, SVHN, and NORB demonstrate the effectiveness of our proposed approach.

关键词： CNN NSGA-II muli-objective optimization image classification Pareto front

来源：评论

学校读者我要写书评

暂无评论

A Discrete Multi-objective Squirrel Search Algorithm for Energy-Efficient Distributed Heterogeneous Permutation Flowshop with Variable Processing Speed

引用

Computers, Materials & Continua 2024年第10期81卷 1757-1787页

作者： Liang Zeng Ziyang Ding Junyang Shi Shanshan Wang School of Electrical and Electronic Engineering Hubei University of TechnologyWuhan430068China Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of TechnologyWuhan430068China Xiangyang Industrial Institute of Hubei University of Technology Xiangyang441100China

In the manufacturing industry,reasonable scheduling can greatly improve production efficiency,while excessive resource consumption highlights the growing significance of energy conservation in *** paper studies the problem of energy-efficient distributed heterogeneous permutation flowshop problem with variable processing speed(DHPFSP-VPS),considering both the minimum makespan and total energy consumption(TEC)as objectives.A discrete multi-objective squirrel search algorithm(DMSSA)is proposed to solve the *** makes four improvements based on the squirrel search ***,in terms of the population initialization strategy,four hybrid initialization methods targeting different objectives are proposed to enhance the quality of initial ***,enhancements are made to the population hierarchy system and position updating methods of the squirrel search algorithm,making it more suitable for discrete scheduling ***,regarding the search strategy,six local searches are designed based on problem characteristics to enhance search ***,a dynamic predator strategy based on Q-learning is devised to effectively balance DMSSA’s capability for global exploration and local ***,two speed control energy-efficient strategies are designed to reduce *** comparative experiments are conducted in this paper to validate the effectiveness of the proposed *** results of comparing DMSSA with other algorithms demonstrate its superior performance and its potential for efficient solving of the DHPFSP-VPS problem.

关键词： Distributed heterogeneous permutation flowshop problem squirrel search algorithm muli-objective optimization energy-efficient variable processing speed

来源：评论

学校读者我要写书评

暂无评论

MULTI-objective optimization OF BUILDING ENVELOPE FOR DAYLIGHT AND ENERGY PERFORMANCE IN HOT AND DRY INDIAN CLIMATE

MULTI-OBJECTIVE OPTIMIZATION OF BUILDING ENVELOPE FOR DAYLIG...

引用

2023 ISES Solar World Congress, SWC 2023

作者： Chaturvedi, Pushpendra Kumar, Nand Lamba, Ravita Nachan, Pushkar Malaviya National Institute of Technology Jaipur India

ISBN: (纸本)9783982040899

The climate-responsive envelope design is the principal component for maintaining the indoor environment. This research presents a multi-objective optimization (MOO) approach to evaluate visual comfort and energy performance. A hypothetical building plan situated in the hot and dry climate of Ahmedabad (23.07° N, 72.63° E), India is chosen as a case study. The optimization was initiated with a Rhinoceros Grasshopper, and the Octopus plugin was used to perform optimization. Spatial Daylight Autonomy (sDA), Spatial Glare Autonomy (sGA), and Energy Use Intensity (EUI) were taken as performance objectives. The design variables such as wall window ratio (WWR), window height, shading configuration, window assembly, wall materials, aspect ratio, building form, and orientation are integrated into the optimization to identify Pareto optimal solutions. This study illustrates that the optimal trade-off solution can reduce the EUI by 31.09% and enhance the sDA and sGA by 93% and 18.58%, respectively, compared to the worst-performing Pareto solutions. The outcomes of this work help building professionals for the designing, and renovation of building envelopes in hot and dry climates and contributing to creating a sustainable built environment. © 2023. The Authors.

关键词： Energy efficiency Envelope design muli-objective optimization Visual comfort

来源：评论

学校读者我要写书评

暂无评论

Introducing the Expohedron for Efficient Pareto-optimal Fairness-Utility Amortizations in Repeated Rankings 22

Introducing the Expohedron for Efficient Pareto-optimal Fair...

引用

15th ACM International Conference on Web Search and Data Mining (WSDM)

作者： Kletti, Till Renders, Jean-Michel Loiseau, Patrick Naver Labs Europe Meylan France Univ Grenoble Alpes INRIA CNRS Grenoble INPLIG Grenoble France

ISBN: (纸本)9781450391320

We consider the problem of computing a sequence of rankings that maximizes consumer-side utility while minimizing producer-side individual unfairness of exposure. While prior work has addressed this problem using linear or quadratic programs on bistochastic matrices, such approaches, relying on Birkhoff-von Neumann (BvN) decompositions, are too slow to be implemented at large scale. In this paper we introduce a geometrical object, a polytope that we call expohedron, whose points represent all achievable exposures of items for a Position Based Model (PBM). We exhibit some of its properties and lay out a Caratheodory decomposition algorithm with complexity O(n(2) log(n)) able to express any point inside the expohedron as a convex sum of at most n vertices, where n is the number of items to rank. Such a decomposition makes it possible to express any feasible target exposure as a distribution over at most n rankings. Furthermore we show that we can use this polytope to recover the whole Pareto frontier of the multi-objective fairness-utility optimization problem, using a simple geometrical procedure with complexity O(n(2) log(n)). Our approach compares favorably to linear or quadratic programming baselines in terms of algorithmic complexity and empirical runtime and is applicable to any merit that is a non-decreasing function of item relevance. Furthermore our solution can be expressed as a distribution over only n permutations, instead of the (n-1)(2) + 1 achieved with BvN decompositions. We perform experiments on synthetic and real-world datasets, confirming our theoretical results.

关键词： ranking fairness amortization pareto-optimal muli-objective optimization Caratheodory expohedron GLS balanced words

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Control of Distributed Parameter Systems in the Case of Interval Uncertainty of the Plant Characteristics

引用

OPTOELECTRONICS INSTRUMENTATION AND DATA PROCESSING 2019年第4期55卷 317-330页

作者： Rapoport, E. Ya Pleshivtseva, Yu E. Samara State Tech Univ Ul Mologvardeiskaya 244 Samara 443100 Russia

The previously developed technology of multi-objective optimization of deterministic systems with distributed parabolic parameters can be applied in typical situations with interval uncertainties of parametric characteristics of controlled plants. Minimax problems of mathematical programming are formed in accordance with a control strategy based on the principle of the best guaranteed result of a expanded set of arguments, which includes all permissible realizations of uncertain factors, in the case of estimating a given accuracy of approximation to a required finite system state in uniform metric. These problems are solved by an alternance method that uses the Chebyshev properties of desired extermals and fundamental laws of the problem domain. This paper also presents an example of multi-objective optimization of temperature modes of induction heating of metallic semifinished products before plastic deformation operations in technological complexes for pressure treatment of metal, which is of independent interest.

关键词： muli-objective optimization distributed parameter systems optimal control minimax estimates interval uncertainty alternance method

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：