检索结果-内蒙古大学图书馆

17th ACM Conference on Recommender Systems (RecSys)

作者： Vente, Tobias Ekstrand, Michael D. Beel, Joeran Univ Siegen Intelligent Syst Grp Siegen Germany Boise State Univ Boise ID USA

ISBN: (纸本)9798400702419

LensKit is one of the first and most popular Recommender System libraries. While LensKit offers a wide variety of features, it does not include any optimization strategies or guidelines on how to select and tune LensKit algorithms. LensKit developers have to manually include third-party libraries into their experimental setup or implement optimization strategies by hand to optimize hyperparameters. We found that 63.6% (21 out of 33) of papers using LensKit algorithms for their experiments did not select algorithms or tune hyperparameters. Non-optimized models represent poor baselines and produce less meaningful research results. This demo introduces LensKit-Auto. LensKit-Auto automates the entire Recommender System pipeline and enables LensKit developers to automatically select, optimize, and ensemble LensKit algorithms.

关键词： Recommender Systems Automated Recommender Systems AutoRecSys algorithm selection Hyperparameter Optimization CASH

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Performance Measurement: Alternatives to PAR10 and Expected Running Time 12th

Multi-objective Performance Measurement: Alternatives to PAR...

引用

12th International Conference on Learning and Intelligent Optimization (LION)

作者： Bossek, Jakob Trautmann, Heike Univ Munster Informat Syst & Stat Munster Germany

ISBN: (纸本)9783030053482;9783030053475

A multiobjective perspective onto common performance measures such as the PAR10 score or the expected runtime of single-objective stochastic solvers is presented by directly investigating the tradeoff between the fraction of failed runs and the average runtime. Multi-objective indicators operating in the bi-objective space allow for an overall performance comparison on a set of instances paving the way for instance-based automated algorithm selection techniques.

关键词： algorithm selection Performance measurement

来源：评论

学校读者我要写书评

暂无评论

A Multi-layer Ontology for Data Processing Techniques 16

A Multi-layer Ontology for Data Processing Techniques

引用

16th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

作者： Man Tianxing Zhukova, Nataly Nguyen Than Nechaev, Alexander Lebedev, Sergey ITMO Univ St Petersburg Russia Russian Acad Sci St Petersburg Inst Informat & Automat St Petersburg Russia St Petersburg Electrotech Univ St Petersburg Russia Vyatka State Univ Kirov Russia

ISBN: (纸本)9789897583803

Currently, data processing technology is applied in various fields. But non-expert researchers are always confused about its diversity and complex processes. Especially due to the instability of real data, the preparation process for extracting information is lengthy. At the same time, different analysis algorithms are based on different mathematical models, so they are suitable for different situations. In the real data processing process, inappropriate data forms and algorithm selections always lead to unsatisfactory results. This paper proposes a multilayer description model of data processing algorithms and implements it based on ontology technology. The model provides a multi-layered structure including data pre-processing, data form conversion, and output model selection so that the user can obtain a complete data processing process from it. The extensibility and interpretability of ontology also provide a huge space for model improvement. The multi-level structure greatly reduces its complexity.

关键词： Data Processing Machine Learning Multilayer Structure algorithm selection Ontology

来源：评论

学校读者我要写书评

暂无评论

A novel performance evaluation system for fluorescent cell image segmentation

A novel performance evaluation system for fluorescent cell i...

引用

1st International Symposium on Computing and Networking (CANDAR)

作者： Takemoto, Satoko Yoshizawa, Shin Tsujimura, Yuki Yokota, Hideo RIKEN Image Proc Res Team Wako Saitama Japan

ISBN: (纸本)9781479927951

Image segmentation is crucial to modern cell biology which depends on quantitative analysis of fluorescent microscopy images. Segmented regions are useful to estimate localization and dynamics of cells and sub-cellular objects. Although many segmentation algorithms have been proposed in image processing and pattern recognition fields, most approaches are designed for some specific tasks and may not work well for other tasks. This makes it difficult to find an algorithm suitable for a given task for biologists who do not have knowledge about segmentation algorithms. Automatic selection of an appropriate segmentation algorithm including its parameters efficiently has become a very important duty, since recent advances in cell and sub-cellular imaging technology significantly increases a number of observed images for biologists. In this paper, we propose a novel segmentation system which has the function of performance evaluation. The set of candidate algorithms including parameter variation are automatically generated by using combinations of the prescribed image processing methods implemented in our system, and the system is designed in order to add and replace these algorithms easily. Their segmentation qualities are evaluated by comparing each result with the ground-truth provided by biologists based on either a single or multiple similarity metrics. Finally, our system predicts which algorithm will provide the best performance on a set of images similar to the original image with ground-truth reference. We examine our system using typical segmentation algorithms under several evaluation metrics and find it useful especially for detection of fluorescent labeled targets with granular shapes on real sub-cellular images, as well as simulated images with small sub-cellular objects.

关键词： Cell image segmentation Performance evaluation algorithm selection Similarity measure fluorescent microscopy image

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Networks as Feature Extractors in Continuous Evolutionary Optimization

Artificial Neural Networks as Feature Extractors in Continuo...

引用

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

Systematic Construction of algorithm Portfolios for a Maintenance Scheduling Problem

Systematic Construction of Algorithm Portfolios for a Mainte...

引用

IEEE Congress on Evolutionary Computation

作者： Almakhlafi, Ahmad Knowles, Joshua Univ Manchester Sch Comp Sci Manchester M13 9PL Lancs England

ISBN: (纸本)9781479904549;9781479904532

We investigate how combinations of evolutionary algorithms (portfolios) can be constructed efficiently for solving optimization problem instances drawn from a distribution. We consider selection methods ranging in intricacy and based on different principles including a technique for efficient tuning of metaheuristics, a racing algorithm. The selectors are used here to optimize instances of the Preventive Maintenance Scheduling Problem (PMSP) in power generation. Experiments show different behaviors of selectors in term of computational time needed to choose constituent algorithms and the performance of the generated portfolios at optimizing previously unseen PMSP instances. The racing selector offers a good trade-off between the computational time and the performance.

关键词： algorithm Portfolio Maintenance Scheduling algorithm selection Genetic algorithms Racing algorithm

来源：评论

学校读者我要写书评

暂无评论

Evolving Instances for Maximizing Performance Differences of State-of-the-Art Inexact TSP Solvers 10th

Evolving Instances for Maximizing Performance Differences of...

引用

10th International Conference on Learning and Intelligent Optimization (LION)

作者： Bossek, Jakob Trautmann, Heike Univ Munster Dept Informat Syst Munster Germany

ISBN: (纸本)9783319503493;9783319503486

Despite the intrinsic hardness of the Traveling Salesperson Problem (TSP) heuristic solvers, e.g., LKH+restart and EAX+restart, are remarkably successful in generating satisfactory or even optimal solutions. However, the reasons for their success are not yet fully understood. Recent approaches take an analytical viewpoint and try to identify instance features, which make an instance hard or easy to solve. We contribute to this area by generating instance sets for couples of TSP algorithms A and B by maximizing/minimizing their performance difference in order to generate instances which are easier to solve for one solver and much harder to solve for the other. This instance set offers the potential to identify key features which allow to distinguish between the problem hardness classes of both algorithms.

关键词： TSP Instance hardness algorithm selection Feature selection

来源：评论

学校读者我要写书评

暂无评论

Understanding TSP Difficulty by Learning from Evolved Instances

引用

4th Conference on Learning and Intelligent Optimization

作者： Smith-Miles, Kate van Hemert, Jano Lim, Xin Yu Monash Univ Sch Math Sci Clayton Vic 3800 Australia Univ Edinburgh Sch Informat Edinburgh EH8 9AB Midlothian Scotland Univ Oxford Math Inst Oxford OX1 3TG England

ISBN: (纸本)9783642137990

Whether the goal is performance prediction, or insights into the relationships between algorithm performance and instance characteristics, a comprehensive set of meta-data from which relationships can be learned is needed. This paper provides a methodology to determine if the meta-data is sufficient, and demonstrates the critical role played by instance generation methods. Instances of the Travelling Salesman Problem (TSP) are evolved using an evolutionary algorithm to produce distinct classes of instances that are intentionally easy or hard for certain algorithms. A comprehensive set of features is used to characterise instances of the TSP, and the impact of these features on difficulty for each algorithm is analysed. Finally, performance predictions are achieved with high accuracy on unseen instances for predicting search effort as well as identifying the algorithm likely to perform best.

关键词： algorithm selection Travelling Salesman Problem Hardness Prediction Phase Transition Combinatorial optimisation Instance Difficulty

来源：评论

学校读者我要写书评

暂无评论

Learning dynamic algorithm portfolios

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2006年第3-4期47卷 295-328页

作者： Gagliolo, Matteo Schmidhuber, Juergen IDSIA CH-6928 Lugano Switzerland Univ Lugano Fac Informat CH-6904 Lugano Switzerland Tech Univ Munich D-85748 Munich Germany

algorithm selection can be performed using a model of runtime distribution, learned during a preliminary training phase. There is a trade-off between the performance of model-based algorithm selection, and the cost of learning the model. In this paper, we treat this trade-off in the context of bandit problems. We propose a fully dynamic and online algorithm selection technique, with no separate training phase: all candidate algorithms are run in parallel, while a model incrementally learns their runtime distributions. A redundant set of time allocators uses the partially trained model to propose machine time shares for the algorithms. A bandit problem solver mixes the model-based shares with a uniform share, gradually increasing the impact of the best time allocators as the model improves. We present experiments with a set of SAT solvers on a mixed SAT-UNSAT benchmark;and with a set of solvers for the Auction Winner Determination problem.

关键词： algorithm selection algorithm portfolios online learning life-long learning bandit problem expert advice survival analysis satisfiability constraint programming

来源：评论

学校读者我要写书评

暂无评论

RANKING MACHINE LEARNING CLASSIFIERS USING MULTICRITERIA APPROACH 11

RANKING MACHINE LEARNING CLASSIFIERS USING MULTICRITERIA APP...

引用

11th International Conference on the Quality of Information and Communications Technology (QUATIC)

作者： de Oliveira Almeida, Filipe Guedes Pereira Rocha Martins, Ana Carolina Rezende dos Santos, Felipe de Moura Bittencourt Reis, Ana Carla Holanda, Maristela Univ Brasilia Comp Sci Brasilia DF Brazil Univ Brasilia Ind Engn Brasilia DF Brazil

ISBN: (纸本)9781538658413

Classification algorithms are widely used as data mining tools for knowledge extraction. The literature presents several classifiers, but none of them applies to all problems. encountered in the various context in which they are used. Faced with this situation, the present article proposes a multi-criteria approach to help practitioners to select the classifiers that will generate the best quality results by observing their performance measures. An empirical study was performed using a baseline of fetal examination from an UCI database using five classification algorithms (C4.5, Naive Bayes, SMO, KNN and Bayesnet), and each classifier was measured using five performance indicators (accuracy, true positive rate, precision, ROC curve and f-measure). Once implemented, a classifier ranking was conducted based on MCDA PROMETHEE II method, and the results show that SMO, C4.5 and Naive Bayes achieved the highest overall ranking.

关键词： MCDA Promethee machine learning algorithm selection classification algorthims

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：