检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Friess, Stephen Tino, Peter Xu, Zhao Menzel, Stefan Sendhoff, Bernhard Yao, Xin Univ Birmingham Sch Comp Sci CERCIA Birmingham W Midlands England NEC Labs Europe GmbH D-69115 Heidelberg Germany Honda Res Inst Europe GmbH D-63073 Offenbach Germany Southern Univ Sci & Technol Shenzhen Peoples R China

ISBN: (纸本)9780738133669

Recent years have seen the advancement of data-driven paradigms in population-based and evolutionary optimization. This reflects on one hand the mere abundance of available data, but on the other hand also progresses in the refinement of previously available machine learning methods. Surprisingly, deep pattern recognition methods emerging from the studies of neural networks have only been sparingly applied. This comes unexpected, as the complex data generated by evolutionary search algorithms can be considered tedious and intractable for manual analysis with mere practical intuitions. In this work, we therefore explore opportunities to employ deep networks to directly learn problem characteristics of continuous optimization problems. Particularly, with data obtained during initial runs of an optimization algorithm. We find that a graph neural network, trained upon a graph representation of continuous search spaces, shows in comparison to more traditional approaches higher validation accuracy and retrieves characteristics within the latent space which are better at distinguishing different continuous optimization problems. We hope that our study can pave the way towards new approaches which allow us to learn problem-dependent algorithm components and recall these from predictions of inputs generated during the run-time of an optimization algorithm.

关键词： Feature learning representation learning algorithm selection graph neural networks knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Improved Automated CASH Optimization with Tree Parzen Estimators for Class Imbalance Problems 8

Improved Automated CASH Optimization with Tree Parzen Estima...

引用

8th IEEE International Conference on Data Science and Advanced Analytics (DSAA)

作者： Duc Anh Nguyen Kong, Jiawen Wang, Hao Menzel, Stefan Sendhoff, Bernhard Kononova, Anna, V Baeck, Thomas Leiden Univ Leiden Inst Adv Comp Sci LIACS Leiden Netherlands Honda Res Inst Europe GmbH HRI EU Offenbach Germany

ISBN: (纸本)9781665420990

The imbalanced classification problem is very relevant in both academic and industrial applications. The task of finding the best machine learning model to use for a specific imbalanced dataset is complicated due to a large number of existing algorithms, each with its own hyperparameters. The Combined algorithm selection and Hyperparameter optimization (CASH) has been introduced to tackle both aspects at the same time. However, CASH has not been studied in detail in the class imbalance domain, where the best combination of resampling technique and classification algorithm is searched for, together with their optimized hyperparameters. Thus, we target the CASH problem for imbalanced classification. We experiment with a search space of 5 classification algorithms, 21 resampling approaches and 64 relevant hyperparameters in total. Moreover, we investigate performance of 2 well-known optimization approaches: Random search and Tree Parzen Estimators approach which is a kind of Bayesian optimization. For comparison, we also perform grid search on all combinations of resampling techniques and classification algorithms with their default hyperparameters. Our experimental results show that a Bayesian optimization approach outperforms the other approaches for CASH in this application domain.

关键词： hyperparameter optimization algorithm selection imbalanced classification CASH optimization

来源：评论

学校读者我要写书评

暂无评论

FLOPs as a Discriminant for Dense Linear Algebra algorithms 22

FLOPs as a Discriminant for Dense Linear Algebra Algorithms

引用

Proceedings of the 51st International Conference on Parallel Processing

作者： Francisco López Lars Karlsson Paolo Bientinesi Department of Computing Science Umeå Universitet Sweden

ISBN: (纸本)9781450397339

Expressions that involve matrices and vectors, known as linear algebra expressions, are commonly evaluated through a sequence of invocations to highly optimised kernels provided in libraries such as BLAS and LAPACK. A sequence of kernels represents an algorithm, and in general, because of associativity, algebraic identities, and multiple kernels, one expression can be evaluated via many different algorithms. These algorithms are all mathematically equivalent (i.e., in exact arithmetic, they all compute the same result), but often differ noticeably in terms of execution time. When faced with a decision, high-level languages, libraries, and tools such as Julia, Armadillo, and Linnea choose by selecting the algorithm that minimises the FLOP count. In this paper, we test the validity of the FLOP count as a discriminant for dense linear algebra algorithms, analysing ”anomalies”: problem instances for which the fastest algorithm does not perform the least number of FLOPs. To do so, we focused on relatively simple expressions and analysed when and why anomalies occurred. We found that anomalies exist and tend to cluster into large contiguous regions. For one expression anomalies were rare, whereas for the other they were abundant. We conclude that FLOPs is not a sufficiently dependable discriminant even when building algorithms with highly optimised kernels. Plus, most of the anomalies remained as such even after filtering out the inter-kernel cache effects. We conjecture that combining FLOP counts with kernel performance models will significantly improve our ability to choose optimal algorithms.

关键词： scientific computing algorithm selection linear algebra

来源：评论

学校读者我要写书评

暂无评论

A comparative study between SA and GA in solving MTSP

A comparative study between SA and GA in solving MTSP

引用

作者： Wenze Zhang Chenyang Xu Electrical and Computer engineering National University of Singapore Mechanical Engineering Shanghai Institute of Technology

The multiple traveling salesmen problems(MTSP) is a combinatorial optimization and np-hard problem. In practice, the computational resource required to solve such problems is usually prohibitive, and, in most cases, using heuristic algorithms is the only practical *** paper implements genetic algorithms(GA) and simulated annealing(SA) to solve the MTSP and does an experimental study based on a benchmark from the TSPLIB instance to compare the performance of two algorithms in reality. The results show that GA can achieve an acceptable solution in a shorter time for any of the MTSP cases and is more accurate when the data size is small. Meanwhile, SA is more robust and achieves a better solution than GA for complex MTSP cases, but it takes more time to converge. Therefore, the result indicates that it is hard to identify which algorithm is comprehensively superior to the other one. However, It also provides an essential reference to developers who want to choose algorithms to solve MTSP in real life,facilitating them to balance the algorithm's performance on different metrics they value.

关键词： multiple travelling salesmen problem (MTSP) NP-hard optimization Simulated Annealing(SA) genetic algorithms(GAs) algorithm comparison algorithm selection

来源：评论

学校读者我要写书评

暂无评论

ACO with automatic parameter selection for a scheduling problem with a group cumulative constraint

ACO with automatic parameter selection for a scheduling prob...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Groleaz, Lucas Ndiaye, Samba N. Solnon, Christine CNRS Infol LIRIS UMR5201 INSA Lyon F-69621 Villeurbanne France Univ Lyon 1 CITI INRIA UMR5201CNRSLIRIS F-69621 Villeurbanne France INSA Lyon CITI INRIA CHROMA F-69621 Villeurbanne France

ISBN: (纸本)9781450371285

We consider a RCPSP (resource constrained project scheduling problem), the goal of which is to schedule jobs on machines in order to minimise job tardiness. This problem comes from a real industrial application, and it requires an additional constraint which is a generalisation of the classical cumulative constraint: jobs are partitioned into groups, and the number of active groups must never exceeds a given capacity (where a group is active when some of its jobs have started while some others are not yet completed). We first study the complexity of this new constraint. Then, we describe an Ant Colony Optimisation algorithm to solve our problem, and we compare three different pheromone structures for it. We study the influence of parameters on the solving process, and show that it varies from an instance to another. Hence, we identify a subset of parameter settings with complementary strengths and weaknesses, and we use a per-instance algorithm selector in order to select the best setting for each new instance to solve. We experimentally compare our approach with a tabu search approach and an exact approach on a data set coming from our industrial application.

关键词： Ant Colony Optimization (ACO) Scheduling Cumulative Constraint algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Automatic recommendation of feature selection algorithms based on dataset characteristics

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 185卷 115589-115589页

作者： Sabino Parmezan, Antonio Rafael Lee, Huei Diana Spolaor, Newton Wu, Feng Chung Univ Sao Paulo Inst Math & Comp Sci Lab Computat Intelligence Av Trabalhador Sao Carlense 400 BR-13566590 Sao Carlos SP Brazil Western Parana State Univ Engn & Exact Sci Ctr Lab Bioinformat Av Tarquinio Joslin dos Santos 1300 BR-85867900 Foz Do Iguacu PR Brazil Univ Estadual Campinas Fac Med Sci Coloproctol Serv Rua Tessalia Vieira de Camargo 126 BR-13083887 Campinas SP Brazil

Feature selection in real-world data mining problems is essential to make the learning task efficient and more accurate. Identifying the best feature selection algorithm, among the many available, is a complex activity that still relies heavily on human experts or some random trial-and-error procedure. Thus, the automated machine learning community has taken some steps towards the automation of this process. In this paper, we address the metalearning challenge of recommending feature selection algorithms by proposing a novel meta-feature engineering model. Our model considers a broad collection of meta-features that enable the study of the relationship between the dataset properties and the feature selection algorithm performance in terms of several criteria. We arrange the input meta-features into eight categories: (i) simple, (ii) statistical, (iii) information-theoretical, (iv) complexity, (v) landmarking, (vi) based on symbolic models, (vii) based on images, and (viii) based on complex networks (graphs). The target meta-features emerge from a multi-criteria performance measure, based on five individual performance indexes, that assesses feature selection methods grounded in information, distance, dependence, consistency, and precision measures. We evaluate our proposal using a recently developed framework that extracts the input meta-features from 213 benchmark datasets, and ranks the assessed feature selection algorithms, to fill in the target meta-features in meta-bases. This evaluation uses five state-of-the-art classification methods to induce recommendation models from meta-bases: C4.5, Random Forest, XGBoost, ANN, and SVM. The results showed that it is possible to reach an average accuracy of up to 90% applying our meta-feature engineering model. This work is the first to use an extensive empirical evaluation to provide a careful discussion of the strengths and limitations of more than 160 meta -features. These meta-features, while designed to aid the task

关键词： Feature engineering Characterization measures algorithm selection Recommendation system Filter Wrapper

来源：评论

学校读者我要写书评

暂无评论

LiBRe: Label-Wise selection of Base Learners in Binary Relevance for Multi-label Classification 18th

LiBRe: Label-Wise Selection of Base Learners in Binary Relev...

引用

18th International Symposium on Intelligent Data Analysis (IDA)

作者： Wever, Marcel Tornede, Alexander Mohr, Felix Hullermeier, Eyke Paderborn Univ Heinz Nixdorf Inst Paderborn Germany Univ La Sabana Cundinamarca Colombia

ISBN: (纸本)9783030445843;9783030445836

In multi-label classification (MLC), each instance is associated with a set of class labels, in contrast to standard classification, where an instance is assigned a single label. Binary relevance (BR) learning, which reduces a multi-label to a set of binary classification problems, one per label, is arguably the most straight-forward approach to MLC. In spite of its simplicity, BR proved to be competitive to more sophisticated MLC methods, and still achieves state-of-the-art performance for many loss functions. Somewhat surprisingly, the optimal choice of the base learner for tackling the binary classification problems has received very little attention so far. Taking advantage of the label independence assumption inherent to BR, we propose a label-wise base learner selection method optimizing label-wise macro averaged performance measures. In an extensive experimental evaluation, we find that or approach, called LiBRe, can significantly improve generalization performance.

关键词： Multi-label classification algorithm selection Binary relevance

来源：评论

学校读者我要写书评

暂无评论

Generating New Space-Filling Test Instances for Continuous Black-Box Optimization

引用

EVOLUTIONARY COMPUTATION 2020年第3期28卷 379-404页

作者： Munoz, Mario A. Smith-Miles, Kate Univ Melbourne Sch Math & Stat Parkville Vic 3010 Australia

This article presents a method to generate diverse and challenging new test instances for continuous black-box optimization. Each instance is represented as a feature vector of exploratory landscape analysis measures. By projecting the features into a two-dimensional instance space, the location of existing test instances can be visualized, and their similarities and differences revealed. New instances are generated through genetic programming which evolves functions with controllable characteristics. Convergence to selected target points in the instance space is used to drive the evolutionary process, such that the new instances span the entire space more comprehensively. We demonstrate the method by generating two-dimensional functions to visualize its success, and ten-dimensional functions to test its scalability. We show that the method can recreate existing test functions when target points are co-located with existing functions, and can generate new functions with entirely different characteristics when target points are located in empty regions of the instance space. Moreover, we test the effectiveness of three state-of-the-art algorithms on the new set of instances. The results demonstrate that the new set is not only more diverse than a well-known benchmark set, but also more challenging for the tested algorithms. Hence, the method opens up a new avenue for developing test instances with controllable characteristics, necessary to expose the strengths and weaknesses of algorithms, and drive algorithm development.

关键词： algorithm selection benchmarking black-box continuous optimization exploratory landscape analysis instance generator

来源：评论

学校读者我要写书评

暂无评论

Selecting appropriate machine learning methods for digital soil mapping

引用

APPLIED MATHEMATICAL MODELLING 2020年第0期81卷 401-418页

作者： Khaledian, Yones Miller, Bradley A. Iowa State Univ Dept Agron Ames IA 50011 USA

Digital soil mapping (DSM) increasingly makes use of machine learning algorithms to identify relationships between soil properties and multiple covariates that can be detected across landscapes. Selecting the appropriate algorithm for model building is critical for optimizing results in the context of the available data. Over the past decade, many studies have tested different machine learning (ML) approaches on a variety of soil data sets. Here, we review the application of some of the most popular ML algorithms for digital soil mapping. Specifically, we compare the strengths and weaknesses of multiple linear regression (MLR), k-nearest neighbors (KNN), support vector regression (SVR), Cubist, random forest (RF), and artificial neural networks (ANN) for DSM. These algorithms were compared on the basis of five factors: (1) quantity of hyperparameters, (2) sample size, (3) covariate selection, (4) learning time, and (5) interpretability of the resulting model. If training time is a limitation, then algorithms that have fewer model parameters and hyperparameters should be considered, e.g., MLR, KNN, SVR, and Cubist. If the data set is large (thousands of samples) and computation time is not an issue, ANN would likely produce the best results. If the data set is small (<100), then Cubist, KNN, RF, and SVR are likely to perform better than ANN and MLR. The uncertainty in predictions produced by Cubist, KNN, RF, and SVR may not decrease with large datasets. When interpretability of the resulting model is important to the user, Cubist, MLR, and RF are more appropriate algorithms as they do not function as "black boxes." There is no one correct approach to produce models for predicting the spatial distribution of soil properties. Nonetheless, some algorithms are more appropriate than others considering the nature of the data and purpose of mapping activity. (C) 2019 Elsevier Inc. All rights reserved.

关键词： algorithm selection Digital soil mapping Machine learning Model evaluation

来源：评论

学校读者我要写书评

暂无评论

Personalized recommendation framework design for online tourism: know you better than yourself

引用

INDUSTRIAL MANAGEMENT & DATA SYSTEMS 2020年第11期120卷 2067-2079页

作者： Wang, Xiaoqian Hubei Univ Econ Sch Tourism & Hotel Management Wuhan Peoples R China

Purpose This study aims to create an idea and a framework to enhance customer stickiness and improve transformation efficiency flow of tourism products from online to offline platforms through the application of personalized recommendation technology. Design/methodology/approach Studies on an overview of progress in current personalized recommendation research, business scenario analysis of online tourism and some possible logical limitations discussion are required for improvement. This study clarifies concepts including online tourism user behavior and generated data, user preference themes and spaces, user models and image and user-product (two-dimensional matrix, etc.). The author then creates a user portrait based on behavior data convergence to locate the user's role from both horizontal and vertical dimensions and also clear the logical levels and associations among them, verifying the similarity in measurement and calculation and optimizing the implementation of the personalized recommendation program under online tourism business scenarios. Findings By providing a framework design about personalized recommendations of online tourism including a flow from data collection to a personalized recommendation algorithm selection, logical analysis is established while the corresponding personalization algorithm is improved. Originality/value This study show a logical shift of personalized recommendations in online tourism management from focusing on the simple collection of travel information and the logical speculation of tourism products to focusing on the individual behavior of potential travelers.

关键词： Personalized recommendation framework Online tourism Individual behavior Preference analysis Persona algorithm selection

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：