检索结果-内蒙古大学图书馆

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Khan, Mohammad Bariq An, Xueli Dressler, Falko Huawei Technol Munich Res Ctr AWTL Munich Germany Tech Univ Berlin Sch Elect Engn & Comp Sci Berlin Germany

ISBN: (纸本)9798350303582;9798350303599

6G mobile communication networks are envisioned to be AI-native, that is, the provision of AI services to users as well as the network itself would be one of the most essential aspect for its system architecture and design. To provide these services and in order to make correct design decisions, deep understanding of the relationship between the wireless networks and the different AI paradigms along with their various functional aspects is needed. In this paper, we explore the relationship in one such AI paradigm, namely federated learning (FL). More specifically, we aim to look at the problem of hyper-parameter optimization (HPO) for hierarchical federated learning by exploring two design scenarios: (1) HPO is carried out at intermediary aggregators which are implemented at edge servers and (2) HPO is realized by a global server such as a cloud-based approach. Empirical results show that although offloading the HPO algorithm completely to the edge-servers does lower the costs, the hybridized approach whereby the global server realizes the HPO algorithm and the edge-server offers some assistance, can provide at least twice as much savings on training costs. We further discuss the two approaches for providing FL as a native service from the mobile communication network and the implications on the network architecture in light of the discussed design scenarios.

关键词： AI-native Networks Hierarchical Federated Learning hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Towards Green AI by Reducing Training Effort of Recurrent Neural Networks Using hyper-parameter optimization with Dynamic Stopping Criteria 22

Towards Green AI by Reducing Training Effort of Recurrent Ne...

引用

22nd IEEE International Symposium on Intelligent Systems and Informatics, SISY 2024

作者： Podgorelec, Vili Fister, Iztok Vrbancic, Grega University of Maribor Intelligent Systems Laboratory Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9798350385601

Neural networks have become a leading model in modern machine learning, able to model even the most complex data. For them to be properly trained, however, a lot of computational resources are required. With the carbon footprint of ever-growing adoption of neural networks in mind, an approach to reduce the required training resources would be very welcome. We designed a new training effort reduction method based on the calculation of area under the normalized loss curve and assessed it on the electricity consumption forecasting problem with the recurrent neural networks. The results show that the proposed method was able to considerably reduce the amount of computational resources, while maintaining the predictive performance, and thus contributing towards the Green AI. © 2024 IEEE.

关键词： Green AI hyper-parameter optimization machine learning neural networks resource optimization

来源：评论

学校读者我要写书评

暂无评论

Improving the Multimodal Classification Performance of Spiking Neural Networks Through hyper-parameter optimization 38

Improving the Multimodal Classification Performance of Spiki...

引用

38th International Conference on Information Networking (ICOIN)

作者： Park, Jin Seon Hong, Choong Seon Kyung Hee Univ Dept Comp Sci & Engn Seoul 446701 South Korea

ISBN: (纸本)9798350330946;9798350330953

Spiking Neural Networks (SNNs) are computational models that emulate the spike-based communication found in biological neural networks. These models are increasingly recognized for their potential to process sensor data in a biologically analogous manner, particularly within multimodal contexts involving both image and audio data. Nonetheless, optimizing the classification performance of deep SNNs is a complex task, frequently impeded by the intricate interactions of hyper-parameters. This paper addresses this challenge by employing advanced hyper-parameter optimization techniques to enhance the classification efficacy of a multimodal SNN. Our work not only refines the performance of SNNs on heterogeneous data types but also elucidates the intricate dynamics between hyper-parameter configurations and classification accuracy within these networks.

关键词： multimodal classification spike SNNs hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization for Latent Spaces 1

引用

21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Veloso, Bruno Caroprese, Luciano Konig, Matthias Teixeira, Sonia Manco, Giuseppe Hoos, Holger H. Gama, Joao Portucalense Univ Porto Portugal Leiden Univ Leiden Netherlands Univ Porto Porto Portugal Univ British Columbia Vancouver BC Canada ICAR CNR Arcavacata Di Rende Italy LIAAD INESC TEC Porto Portugal

ISBN: (数字)9783030865238

ISBN: (纸本)9783030865238;9783030865221

We present an online optimization method for time-evolving data streams that can automatically adapt the hyper-parameters of an embedding model. More specifically, we employ the Nelder-Mead algorithm, which uses a set of heuristics to produce and exploit several potentially good configurations, from which the best one is selected and deployed. This step is repeated whenever the distribution of the data is changing. We evaluate our approach on streams of real-world as well as synthetic data, where the latter is generated in such way that its characteristics change over time (concept drift). Overall, we achieve good performance in terms of accuracy compared to state-of-the-art AutoML techniques.

关键词： AutoML hyper-parameter optimization Latent spaces Nelder-Mead algorithm SMAC Recommender systems

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization for Deep Learning by Surrogate-based Model with Weighted Distance Exploration

Hyper-Parameter Optimization for Deep Learning by Surrogate-...

引用

IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Li, Zhenhua Shoemaker, Christine A. Nanjing Univ Aeronaut & Astronaut Sch Comp Sci & Technol Nanjing Peoples R China Natl Univ Singapore Dept Ind Syst Engn Singapore Singapore

ISBN: (纸本)9781728183923

To improve deep neural net hyper-parameter optimization we develop a deterministic surrogate optimization algorithm as an efficient alternative to Bayesian optimization. A deterministic Radial Basis Function (RBF) surrogate model is built to interpolate previously evaluated points, and this surrogate model is incrementally updated in each iteration. The stochastic algorithm CMA-ES is used to search the acquisition function based on the surrogate. The acquisition function at a point is based on a weighted average of the surrogate at x and the minimum distance from x to a previously evaluated point. We evaluate the proposed algorithm RBF-CMA on hyper-parameter optimization tasks for deep convolutional neural networks on datasets of CIFAR-10, SVHN, and CIFAR-100. We show that RBF-CMA achieves a promising performance especially when the search space dimension is high in comparison to other algorithms including GP-EI, GP-LCB, and SMBO.

关键词： hyper-parameter optimization deep neural networks surrogate optimization radial basis function

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning with Adaptive Client-Side hyper-parameter optimization 43

Efficient Federated Learning with Adaptive Client-Side Hyper...

引用

43rd IEEE International Conference on Distributed Computing Systems (ICDCS)

作者： Kundroo, Majid Kim, Taehong Chungbuk Natl Univ Sch Informat & Commun Engn Cheongju South Korea

ISBN: (纸本)9798350339864

Federated Learning (FL) trains machine learning (ML) models with privacy protection. However, current FL algorithms use the same hyper-parameters for all clients regardless of their statistical or system heterogeneity, leading to slower convergence. Convergence time and communication rounds may be reduced by using appropriate values for hyper-parameters like learning rate and epochs. We present an adaptive client-side hyper-parameter optimization algorithm, FedAdap, that uses metrics gathered during model training to optimize hyper-parameters on each client and can be used in conjunction with any other FL algorithm. Preliminary results show that FedAdap enhances the performance of existing FL algorithms by decreasing convergence time by up to 34% and reducing communication rounds by up to 37% in the case of IID data. Moreover, in non-IID data settings, the convergence time is reduced by up to 82.5% and the number of communication rounds is reduced by up to 77%.

关键词： Federated Learning hyper-parameter optimization Convergence Communication cost

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization of Classifiers, Using an Artificial Immune Network and Its Application to Software Bug Prediction

引用

IEEE ACCESS 2020年 8卷 20954-20964页

作者： Khan, Faiza Kanwal, Summrina Alamri, Sultan Mumtaz, Bushra Riphah Int Univ Fac Comp Islamabad 45211 Pakistan Saudi Elect Univ Dept Comp & Informat Riyadh 11673 Saudi Arabia

Software testing is an important task in software development activities, and it requires most of the resources, namely, time, cost and effort. To minimize this fatigue, software bug prediction (SBP) models are applied to improve the software quality assurance (SQA) processes by predicting buggy components. The bug prediction models use machine learning classifiers so that bugs can be predicted in software components in some software metrics. These classifiers are characterized by some configurable parameters, called hyper-parameters that need to be optimized to ensure better performance. Many methods have been proposed by researchers to predict the defective components but these classifiers sometimes not perform well when default settings are used for machine learning classifiers. In this paper, software bug prediction model is proposed which uses machine learning classifiers in conjunction with the Artificial Immune Network (AIN) to improve bug prediction accuracy through its hyper-parameter optimization. For this purpose, seven machine learning classifiers, such as support vector machine Radial base function (SVM-RBF), K-nearest neighbor (KNN) (Minkowski metric), KNN (Euclidean metric), Naive Bayes (NB), Decision Tree (DT), Linear discriminate analysis (LDA), Random forest (RF) and adaptive boosting (AdaBoost), were used. The experiment was carried out on bug prediction dataset. The results showed that hyper-parameter optimization of machine learning classifiers, using AIN and its applications for software bug prediction, performed better than when classifiers with their default hyper-parameters were used.

关键词： Artificial immune network (AIN) artificial immune system (AIS) hyper-parameter optimization optimized artificial immune network (opt-aiNet) software bug prediction (SBP)

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization in classification: To-do or not-to-do

引用

PATTERN RECOGNITION 2020年 103卷 107245-107245页

作者： Ngoc Tran Schneider, Jean-Guy Weber, Ingo Qin, A. K. Swinburne Univ Technol Dept Comp Sci & Software Engn Hawthorn Vic 3122 Australia Deakin Univ Sch Informat Technol Geelong Vic Australia CSIRO Data61 Eveleigh NSW 2015 Australia Tech Univ Berlin Chair Software & Business Engn Berlin 10587 Germany Swinburne Univ Technol Hawthorn Vic Australia

hyper-parameter optimization is a process to find suitable hyper-parameters for predictive models. It typically incurs highly demanding computational costs due to the need of the time-consuming model training process to determine the effectiveness of each set of candidate hyper-parameter values. A priori, there is no guarantee that hyper-parameter optimization leads to improved performance. In this work, we propose a framework to address the problem of whether one should apply hyper-parameter optimization or use the default hyper-parameter settings for traditional classification algorithms. We implemented a prototype of the framework, which we use a basis for a three-fold evaluation with 486 datasets and 4 algorithms. The results indicate that our framework is effective at supporting modeling tasks in avoiding adverse effects of using ineffective optimizations. The results also demonstrate that incrementally adding training datasets improves the predictive performance of framework instantiations and hence enables "life-long learning." (C) 2020 Elsevier Ltd. All rights reserved.

关键词： hyper-parameter optimization Framework Bayesian optimization Machine learning Incremental learning

来源：评论

学校读者我要写书评

暂无评论

hyper-parameter optimization Using MARS Surrogate for Machine-Learning Algorithms

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2020年第3期4卷 287-297页

作者： Li, Yangyang Liu, Guangyuan Lu, Gao Jiao, Licheng Marturi, Naresh Shang, Ronghua Xidian Univ Int Res Ctr Intelligent Percept & Computat Sch Artificial IntelligenceJoint Int Res Lab Int Minist EducKey Lab Intelligent Percept & Image U Xian 710071 Peoples R China Univ Birmingham Extreme Robot Lab Edgbaston B15 2TT England

Automatically searching for optimal hyper parameters is of crucial importance for applying machine learning algorithms in practice. However, there are concerns regarding the tradeoff between efficiency and effectiveness of current approaches when faced with the expensive function evaluations. In this paper, a novel efficient hyper-parameter optimization algorithm is proposed (called MARSAOP), in which multivariate spline functions are used as surrogate and dynamic coordinate search approach is employed to generate the candidate points. Empirical studies on benchmark problems and machine-learning models (e.g.,SVM, RE, and NN) demonstrate that the proposed algorithm is able to find relatively high-quality solutions for benchmark problems and excellent hyper-parameter configurations for machine-learning models using a limited computational budget (few function evaluations).

关键词： hyper-parameter optimization MARS dynamic coordinate search machine learning

来源：评论

学校读者我要写书评

暂无评论

Grid search with a weighted error function: hyper-parameter optimization for financial time series forecasting

引用

APPLIED SOFT COMPUTING 2024年 154卷

作者： Zhao, Yuan Zhang, Weiguo Liu, Xiufeng South China Univ Technol Sch Business Adm Guangzhou 510641 Peoples R China Guangzhou Financial Serv Innovat & Risk Management Guangzhou 510641 Peoples R China Shenzhen Univ Coll Management Shenzhen 518060 Peoples R China Tech Univ Denmark Dept Technol Management & Econ DK-2800 Lyngby Denmark

Financial time series forecasting is a difficult task due to the complexity and volatility of financial markets. Machine learning models have been applied to tackle this task, but finding their optimal hyper -parameters with less time and ensuring the prediction accuracy of models are still significant challenges. Existing methods such as GridSearch with cross -validation (GridsearchCV) for optimizing the hyper -parameters are time-consuming for complex models or large search spaces, and they do not ensure that the model has excellent predictive accuracy. To address these challenges, we propose a novel method called GridsearchWEF that uses grid search with a weighted error function. This method aims to reduce the time cost of hyperparameter optimization for machine learning models and guarantee their prediction performance. We conduct an empirical analysis of crude oil return forecasting using four machine learning models: RF, GBDT, SVR, and LASSO. We compare the performance of these models using GridsearchCV, random search with cross -validation (RandomizedSearchCV), Bayes optimization with cross -validation (BayesSearchCV), and GridsearchWEF. The results show that GridsearchWEF outperforms the other methods in terms of hyper -parameter optimization, modeling efficiency, prediction accuracy, and economic values. In particular, the time of all models using GridSearchWEF is less than 30 s, which is much less than other algorithms. GridsearchWEF is a more efficient and superior method for hyper -parameter optimization in financial time series forecasting.

关键词： Time series forecasting Machine learning hyper-parameter optimization Modeling efficiency Economic value

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：