检索结果-内蒙古大学图书馆

IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS)

作者： Zhang, Kehao Jin, Huaiping Jin, Huaikang Wang, Bin Yu, Wangyang Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming 650500 Peoples R China Huaneng Renewables Co Ltd Yunnan Branch Kunming 650000 Peoples R China Wuhan Maritime Commun Res Inst Wuhan 430233 Peoples R China

ISBN: (纸本)9798350321050

Wind energy has become an important part of national power systems due to its wide distribution, low cost, and non-polluting characteristics. However, the intermittence, randomness, and fluctuating of wind energy make it extremely difficult to connect wind power to the grid, which in turn affects the normal dispatch of power resources. Therefore, accurate wind power forecasting is crucial for power systems. Deep neural networks (DNNs) can efficiently capture high-dimensional nonlinear spatiotemporal features and are employed. The architectures of state-of-the-art DNNs are usually hand-designed by users with extensive expertise. In this paper, a gated recurrent unit neural networks for wind power forecasting approach based on surrogate-assisted evolutionary neural architecture search (SA-ENAS) is proposed. Firstly, SA-ENAS uses gated recurrent unit neural networks (GRU) to capture high-dimensional nonlinear spatiotemporal features, while incorporating delay variables into ENAS. Secondly, the GRU architecture is jointly encoded with delay variables. Then, the architecture search and delay variable selection are achieved using a surrogate model based ENAS approach. Finally, the effectiveness and superiority of the proposed method are verified through the case study of an actual wind farm dataset.

关键词： Wind power forecasting evolutionary neural architecture search Gated recurrent unit neural networks Surrogate model Delay variable selection

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection in time-series data using evolutionary neural architecture search with non-differentiable functions

引用

APPLIED SOFT COMPUTING 2024年 155卷

作者： Gomez-Rosero, Santiago Capretz, Miriam A. M. Western Univ Dept Elect & Comp Engn London ON N6A 3K7 Canada

Deep neural networks have become the benchmark in diverse fields such as energy consumption forecasting, speech recognition, and anomaly detection, owing to their ability to efficiently process and analyse data. However, they face challenges in managing the complexity and variability in time series data, often leading to increased model complexity and prolonged search duration during parameter tuning. This paper proposes a novel anomaly detection approach through evolutionary neural architecture search (AD-ENAS), which is specifically designed for time series data. The proposed approach focuses on the search for the optimal and minimal neural network architecture. The AD-ENAS method consists of two main phases: architecture evolution and weight adjustment. The architecture evolution phase highlights the importance of neural network architecture by evaluating the fitness of each network agent using shared weight values. Subsequently, the convolutional matrix adaptation technique is used in the next phase for optimal weight adjustment of the neural network. The proposed AD-ENAS method operates without relying on differentiable functions, thus expanding the scope of neural network design beyond traditional backpropagation-based approaches. Various non -differentiable loss functions are explored to facilitate effective architecture search and weight adjustment. Comparative experiments are conducted with five baseline anomaly detection methods on three well-known datasets from reputable sources such as NASA SMAP, NASA MSL and Yahoo S5 -A1. The results demonstrate that the AD-ENAS approach effectively evolves neural network architectures, outperforming baseline methods with F1 scores across the three datasets (MSL: 0.942, SMAP: 0.961, Yahoo S5 -A1: 0.988) with non -differentiable loss functions, showcasing its efficacy in detecting anomalies in time series data.

关键词： evolutionary neural architecture search Anomaly detection Time series data Shared weights Evolution strategies Non-differentiable functions

来源：评论

学校读者我要写书评

暂无评论

Wind power forecasting based on ensemble deep learning with surrogate-assisted evolutionary neural architecture search and many-objective federated learning

引用

ENERGY 2024年 308卷

作者： Jin, Huaiping Zhang, Kehao Fan, Shouyuan Jin, Huaikang Wang, Bin Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Peoples R China Kunming Univ Sci & Technol Higher Educ Key Lab Ind Intelligence & Syst Yunnan Kunming 650500 Peoples R China China Resources New Energy Investment Co Ltd Sichuan Branch Chengdu 610066 Sichuan Peoples R China China Energy Engn Grp Yunnan Elect Power Design In Kunming 650051 Peoples R China Huaneng Renewables Co Ltd Yunnan Branch Kunming 655000 Peoples R China

Deep neural networks (DNN) have been widely used in wind power forecasting (WPF), however, they still encounter difficulties such as delayed variable selection, DNN architecture design, and network weight optimization. Therefore, an ensemble cascaded DNN (ECDNN) with surrogate-assisted evolutionary neural architecture search (SEANS) and many-objective federated learning (MOFL) is proposed and referred to as ECDNNSENAS-MOFL. SEANS is proposed to determine the delayed variables and network architecture efficiently, which allows significantly enhancing the evolutionary search efficiency than traditional evolutionary neural architecture search (ENAS) approaches by employing a surrogate model to achieve fast fitness evaluations. Meanwhile, MOFL is developed by embedding the federated learning into many-objective optimization to obtain more reliable network weights based on the distributed modeling data than traditional centralized learning and federated learning, as well as solving the problems of data privacy protection and data islands. Furthermore, selective ensemble learning is introduced to build high-performance ensemble WPF model by combining the merits of multiple highly influential Pareto solutions. The effectiveness and superiority of the proposed ECDNNSENAS-MOFL method are verified using an actual wind power dataset. The application results show that the proposed method can provide new insights into data-driven WPF modeling and has a great potential for practical applications.

关键词： Wind power forecasting Cascaded deep neural network evolutionary neural architecture search Delayed variable selection Many-objective federated learning Selective ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid architecture-Based evolutionary Robust neural architecture search

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2024年第4期8卷 2919-2934页

作者： Yang, Shangshang Sun, Xiangkun Xu, Ke Liu, Yuanchao Tian, Ye Zhang, Xingyi Anhui Univ Sch Artificial Intelligence Key Lab Intelligent Comp & Signal Proc Minist Educ Hefei 230601 Peoples R China Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Anhui Univ Sch Comp Sci & Technol Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China

The robustness of neural networks in image classification is important to resist adversarial attacks. Although many researchers proposed to enhance the network robustness by inventing network training paradigms or designing network architectures, existing approaches are mainly based on a single type of networks, e.g., convolution neural networks (CNNs) or vision Transformer (ViT). Considering a recently revealed fact that CNNs and ViT can effectively defend against adversarial attacks transferred from each other, this paper aims to enhance network robustness by designing robust hybrid architecture networks containing different types of networks. To this end, we propose a hybrid architecture-based evolutionary neural architecture search approach for robust architecture design, termed HA-ENAS. Specifically, to combine or aggregate different types of networks in the same network framework, a multi-stage block-wise hybrid architecture network is first devised as the supernet, where three types of blocks (called convolution blocks, Transformer blocks, multi-layer perception blocks) are further designed as each block's candidate, and thus a hybrid architecture-based search space is established for HA-ENAS;then, the robust hybrid architecture search is formulated as an optimization problem maximizing both clean and adversarial accuracy of architectures, and an efficient multi-objective evolutionary algorithm is employed to solve the problem, where a supernet-based retraining evaluation and a surrogate model are used to mitigate coupled weight influence and reduce the whole search cost. Experimental results show that the hybrid architectures found by the proposed HA-ENAS outperform state-of-the-art single-type architectures in terms of clean accuracy and adversarial accuracy under a variety of common attacks.

关键词： Computer architecture Robustness search problems Training Space exploration Network architecture Transformers Networks robustness hybrid architectures evolutionary neural architecture search surrogate-assisted

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Wind Power Forecasting Method Integrating architecture Comparison-based evolutionary neural architecture search

Deep Learning Wind Power Forecasting Method Integrating Arch...

引用

第43届中国控制会议

作者： Wang Zhou Yundong Cao Huaikang Jin Shouyuan Fan Bin Wang Huaiping Jin Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Huaneng Renewables Co. Ltd.Yunnan Branch China Energy Engineering Group Yunnan Electric Power Design Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Wind energy has become an important part of the power system due to its versatility,low cost,and environmental ***,the instability and volatility of wind energy pose a huge challenge to the grid-connected operation of wind power,affecting the effective scheduling of the power *** this situation,accurate forecasting of wind power becomes crucial,and deep neural networks have been widely used in this field due to their excellent ability to process high-dimensional nonlinear spatiotemporal ***,excellent deep neural network architectures are often manually designed by users with extensive expertise,which is time-consuming and results in high *** order to automatically design suitable deep neural network architectures for different wind power forecasting tasks,this paper proposes a deep learning wind power forecasting method based on architecture comparison evolutionary neural architecture *** method first encodes neural network architectures and then uses evolutionary algorithms to search for the optimal *** them,to address the problem of slow fitness calculation in evolutionary algorithms,architectures comparison-based the method is used instead of fitness calculation for architecture search,greatly accelerating search *** effectiveness and superiority of the proposed method were verified through case studies on actual wind farm datasets.

关键词： Wind Power Forecasting evolutionary neural architecture search architecture Comparator architecture Encoding

来源：评论

学校读者我要写书评

暂无评论

Accelerating Gene-pool Optimal Mixing evolutionary Algorithm for neural architecture search with Synaptic Flow

Accelerating Gene-pool Optimal Mixing Evolutionary Algorithm...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Khoa Huu Tran Luc Truong An Vo Ngoc Hoang Luong Univ Informat Technol Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam

ISBN: (纸本)9798400701207

This study experiments the integration of the zero-cost proxy metric Synaptic Flow with the Gene-pool Optimal Mixing (GOM) crossover to efficiently generate new candidates during an evolutionary neural architecture search (ENAS). Our experiments demonstrate that the Gene-pool Optimal Mixing evolutionary Algorithm (GOMEA) with Synaptic Flow can obtain top-performing architectures with a small additional overhead compared to a classic Genetic Algorithm. Code is available at: https://***/ELO-Lab/SF-GOMENAS.

关键词： evolutionary neural architecture search evolutionary algorithms optimal mixing synaptic flow

来源：评论

学校读者我要写书评

暂无评论

Speeding up the Multi-objective NAS Through Incremental Learning 23rd

Speeding up the Multi-objective NAS Through Incremental Lear...

引用

23rd Mexican International Conference on Artificial Intelligence

作者： Garcia-Garcia, Cosijopii Derbel, Bilel Morales-Reyes, Alicia Jair Escalante, Hugo Inst Nacl Astrofis Opt & Electr Luis Enrique Erro 1 Cholula 72840 Puebla Mexico Univ Lille CNRS Inria Cent LilleUMR 9189 CRIStAL F-59000 Lille France

ISBN: (纸本)9783031755422;9783031755439

Deep neural networks (DNNs), particularly convolutional neural networks (CNNs), have garnered significant attention in recent years for addressing a wide range of challenges in image processing and computer vision. neural architecture search (NAS) has emerged as a crucial field aiming to automate the design and configuration of CNN models. In this paper, we propose a novel strategy to speed up the performance estimation of neural architectures by gradually increasing the size of the training set used for evaluation as the search progresses. We evaluate this approach using the CGP-NASV2 model, a multi-objective NAS method, on the CIFAR-100 dataset. Experimental results demonstrate a notable acceleration in the search process, achieving a speedup of 4.6 times compared to the baseline. Despite using limited data in the early stages, our proposed method effectively guides the search towards competitive architectures. This study highlights the efficacy of leveraging lower-fidelity estimates in NAS and paves the way for further research into accelerating the design of efficient CNN architectures.

关键词： evolutionary neural architecture search AutoML Lower fidelity estimates

来源：评论

学校读者我要写书评

暂无评论

An evolutionary search algorithm for efficient ResNet-based architectures: a case study on gender recognition

An evolutionary search algorithm for efficient ResNet-based ...

引用

IEEE Congress on evolutionary Computation (CEC)

作者： Fernandes da Silva, Andre Ramos Pavelski, Lucas Marcondes Queiroz Cordovil Junior, Luiz Alberto de Oliveira Gomes, Paulo Henrique Azevedo, Layane Menezes Fernandes Junior, Francisco Erivaldo Sidia R&D Inst Retail Management Syst Res Grp Sidia Amazon TowerDarcy Vargas Ave 654 BR-69055035 Manaus Amazonas Brazil

ISBN: (数字)9781665467087

ISBN: (纸本)9781665467087

neural architecture search (NAS) is a busy research field growing exponentially in recent years. State-of-the-art deep neural networks usually require a specialist to fine-tune the model to solve a specific problem. NAS research aims to design neural network architectures automatically, thus easing the need for machine learning specialists to spend a lot of effort on hand-crafted attempts. As artificial intelligence applications are becoming ubiquitous, there is also a growing interest in efficient applications that could be deployed to smartphones, smart wearable devices, and other edge devices. Gender recognition in unfiltered images - such as those we find in real-world situations like pictures taken with smartphones and video shots from surveillance cameras - is one of such challenging applications. In this work, we developed an evolutionary NAS algorithm that consistently finds efficient ResNet-based architectures, named RENNAS, which have a good trade-off between classification accuracy and architectural and computational complexities. We demonstrate our algorithm's performance on Adience dataset of unfiltered images for gender recognition.

关键词： evolutionary neural architecture search Residual neural Networks Genetic Algorithms Computer Vision Gender Recognition

来源：评论

学校读者我要写书评

暂无评论

An efficient evolutionary architecture search for variational autoencoder with alternating optimization and adaptive crossover

引用

SWARM AND evolutionary COMPUTATION 2024年 86卷

作者： Shang, Ronghua Liu, Hangcheng Li, Wenzheng Zhang, Weitong Ma, Teng Jiao, Licheng Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ Xian Shaanxi Peoples R China Xidian Univ Guangzhou Inst Technol Guangzhou Guangdong Peoples R China Air Force Engn Univ Informat & Nav Coll Xian Shaanxi Peoples R China

Variational autoencoder is a commonly unsupervised learning model. However, its complex structure hinders the utilization of the network architecture search algorithm to release researchers from tedious manual design. To design excellent architectures automatically, this paper proposes an efficient evolutionary architecture search for variational autoencoder with alternating optimization and adaptive crossover(AOC-VAE). Firstly, to alleviate the problem of large search space when automatically designing variational autoencoders, AOC-VAE designs an alternating optimized search mechanism based on the specific coupling of encoder and decoder in variational autoencoders, which reduces the original huge search space almost to half. Then, AOC-VAE can find quickly the optimal individual in the solution space by designing an adaptive crossover mechanism. In early evolutionary period, the structural differences between individuals are relatively significant, making crossover operations more inclined to exchange structural information between individuals. As evolution progresses, the individual structures in the population tend to be similar, and the exchange of information concentrates on the parameter. Finally, in the optimization process, a fitness evaluation mechanism based on dynamic weights is designed to accurately find out the outstanding individuals under the current optimization goal. Individual fitness in the population is more inclined to be affected by the current optimization goal, thus guiding the population to evolve according to the optimization goal at different stages. AOC-VAE is verified on MNIST, SVHN, CIFAR-10, and CIFAR-100 benchmark datasets and compared with 14 algorithms. The experimental results show that the VAE network structure designed by the AOC-VAE performs well in the image classification task.

关键词： Variational autoencoders Genetic algorithms evolutionary neural architecture search Image classification

来源：评论

学校读者我要写书评

暂无评论

evolutionary architecture search via adaptive parameter control and gene potential contribution

引用

SWARM AND evolutionary COMPUTATION 2023年 82卷

作者： Shang, Ronghua Zhu, Songling Liu, Hangcheng Ma, Teng Zhang, Weitong Feng, Jie Jiao, Licheng Stolkin, Rustam Xidian Univ Sch Artificial Intelligence Key Lab Intelligent Percept & Image Understanding Minist Educ Xian 710071 Shaanxi Peoples R China AF Engn Univ Coll Informat & Nav Xian 710071 Shaanxi Peoples R China Univ Birmingham Birmingham England

evolutionary neural architecture search (ENAS) algorithms benefit from the non-convex optimization capability of evolutionary computation. However, most ENAS algorithms use a genetic algorithm (GA) with fixed parameter settings, which limits the algorithm's search performance. Furthermore, the information generated during the evolutionary process is often ignored, while this information can be helpful for guiding the evolutionary direction of the population. This paper proposes a novel ENAS algorithm based on adaptive parameter control and gene potential contribution (AG-ENAS) to evolve neural networks efficiently. Firstly, an adaptive parameter adjustment mechanism is designed, based on population diversity and fitness. This enables better-informed adaptation of related parameters of genetic operators. Secondly, the mutation operator guided by the gene potential contribution of genes tends to produce better offspring. The gene potential contribution reflects the positive effect of the current gene on fitness. It guides the evolution by weighting the more valuable genes with the distribution index matrix. Finally, the concept of aging is introduced into the environmental selection, to offer more opportunities to the young generation and alleviate premature convergence. The proposed algorithm has been evaluated on eight different datasets, and compared against 44 state-of-the-art algorithms from the literature. The experimental results show that the network designed by AG-ENAS obtains higher classification accuracy than manual-designed networks such as SENet, DenseNet, and other ENAS algorithms such as Large-Evo and AE-CNN.

关键词： evolutionary neural architecture search Genetic algorithm Guided mutation Image classification

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：