检索结果-内蒙古大学图书馆

Applicability evaluation of selected xAI methods for machine learning algorithms for signal parameters extraction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dimitrova, Kalina Kozhuharov, Venelin Petkov, Peicho Faculty of Physics Sofia University St. Kliment Ohridski 5 J. Bourchier Blvd. Sofia1164 Bulgaria

Machine learning methods find growing application in the reconstruction and analysis of data in high energy physics experiments. A modified convolutional autoencoder model was employed to identify and reconstruct the pulses from scintillating crystals. The model was further investigated using four xAI methods for deeper understanding of the underlying reconstruction mechanism. The results are discussed in detail, underlining the importance of xAI for knowledge gain and further improvement of the algorithms. © 2025, CC BY.

关键词： learning algorithms

Federated learning algorithms: Towards Next Generation Communication Systems 3

学校读者我要写书评

暂无评论

Federated Learning Algorithms: Towards Next Generation Commu...

3rd World Symposium on Communication Engineering, WSCE 2020

作者： Stergiou, Konstantinos D. Psannis, Konstantinos E. University of Macedonia Department of Applied Informatics Thessaloniki Greece

ISBN: (纸本)9781728185644

We provide a survey of four different categories of Federated learning algorithms and their limitations as these were unveiled through experiments using commonly accepted data sets. The level of data heterogeneity forms a potential benchmark to compare Federated Averaging, Gradient Descent, Evolutionary, and Differential Privacy methods and, among other criteria, identifies the gaps that need to be addressed from future approaches. © 2020 IEEE.

关键词： learning algorithms

Development of a Diagnostic Tool for the Validity of Multiple-Choice Blank-Filling Questions for learning algorithms with C Programming Language 9

学校读者我要写书评

暂无评论

Development of a Diagnostic Tool for the Validity of Multipl...

9th International Congress on Advanced Applied Informatics, IIAI-AAI 2020

作者： Ohno, Akifumi Matsumoto, Shimpei Hiroshima Institute of Technology Graduate School of Science and Technology Hirosima Japan Hiroshima Institute of Technology Faculty of Applied Information Science Hirosima Japan

ISBN: (纸本)9781728173979

In many programming educations, as a means of checking learner's comprehension relatively easily than code description, an assignment in the form of closed-ended questions is presented. The closed-ended question is not a task to create all the source code from scratch, but to create sources using pre-supplied materials. Closed-ended questions include the completion of some statements, reordering of some statements, and template modification. When giving the learning task with closed-ended questions, the instructor usually has to design the problem-solving procedure in advance by only himself. At this time, it is important to prevent unintended correct answers due to the instructor's oversight, but this task is not easy. Therefore, in this study, we focus on multiple-choice blank-filling questions as a closed-ended question and develop a diagnostic tool to confirm its adequacy. As a result of practice, our diagnostic tool could find correct answers that the instructor could not have noticed and behaviors specific to the C language. © 2020 IEEE.

关键词： learning algorithms

A study of machine learning algorithms on email spam classification 35

学校读者我要写书评

暂无评论

A study of machine learning algorithms on email spam classif...

35th International Conference on Computers and Their Applications, CATA 2020

作者： Sutta, N. Liu, Z. Zhang, X. Department of Computer Science Southeast Missouri State University Missouri United States

Despite the fact that different techniques have been developed to filter spam, due to the spammer’s rapid adoption of new spam detection techniques, we are still overwhelmed with spam emails. Currently, machine learning techniques are the most effective ways to classify and filter spam emails. In this paper, a comprehensive comparison and analysis of the performance of various classification models on the 2007 TREC Public Spam Corpus are exhibited in various cases of without or with N-Grams as well as using separate or combined datasets. It is shown that the inclusion of the N-Grams in the pre-processing phase provides high accuracy results for classification models in most of the cases, and the models using the split approach with combined datasets give better results than models using the separate dataset. © 2020, EasyChair. All rights reserved.

关键词： learning algorithms

Big data analytics applying the fusion approach of multicriteria decision making with deep learning algorithms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Papineni, Swarajya Lakshmi V. Yarlagadda, Snigdha Akkineni, Harita Reddy, A. Mallikarjuna Department of Information Technology Prasad V Potluri Siddhartha Institute of Technology Vijayawada AP India Technology Analyst Infosys Limited Bangalore Karnataka India Department of CSE Anurag University Hyderabad AP India

Data is evolving with the rapid progress of population and communication for various types of devices such as networks, cloud computing, Internet of Things (IoT), actuators, and sensors. The increment of data and communication content goes with the equivalence of velocity, speed, size, and value to provide the useful and meaningful knowledge that helps to solve the future challenging tasks and latest issues. Besides, multicriteria based decision making is one of the key issues to solve for various issues related to the alternative effects in big data analysis. It tends to find a solution based on the latest machine learning techniques that include algorithms like decision making and deep learning mechanism based on multicriteria in providing insights to big data. On the other hand, the derivations are made for it to go with the approximations to increase the duality of runtime and improve the entire system's potentiality and efficacy. In essence, several fields, including business, agriculture, information technology, and computer science, use deep learning and multicriteria-based decision-making problems. This paper aims to provide various applications that involve the concepts of deep learning techniques and exploiting the multicriteria approaches for issues that are facing in big data analytics by proposing new studies with the fusion approaches of data-driven techniques. © 2021, CC BY-NC-ND.

关键词： learning algorithms

Comparison of Semi-supervised Deep learning algorithms for Audio Classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cances, Léo Labbé, Etienne Pellegrini, Thomas IRIT University of Toulouse CNRS Toulouse France Toulouse France

In this article, we adapted five recent SSL methods to the task of audio classification. The first two methods, namely Deep Co-Training (DCT) and Mean Teacher (MT), involve two collaborative neural networks. The three other algorithms, called MixMatch (MM), ReMixMatch (RMM), and FixMatch (FM), are single-model methods that rely primarily on data augmentation strategies. Using the Wide-ResNet-28-2 architecture in all our experiments, 10% of labeled data and the remaining 90% as unlabeled data for training, we first compare the error rates of the five methods on three standard benchmark audio datasets: Environmental Sound Classification (ESC-10), UrbanSound8K (UBS8K), and Google Speech Commands (GSC). In all but one cases, MM, RMM, and FM outperformed MT and DCT significantly, MM and RMM being the best methods in most experiments. On UBS8K and GSC, MM achieved 18.02% and 3.25% error rate (ER) respectively, outperforming models trained with 100% of the available labeled data, which reached 23.29% and 4.94%, respectively. RMM achieved the best results on ESC-10 (12.00% ER), followed by FM which reached 13.33%. Second, we explored adding the mixup augmentation, used in MM and RMM, to DCT, MT and FM. In almost all cases, mixup brought consistent gains. For instance, on GSC, FM reached 4.44% and 3.31% ER without and with mixup. Our PyTorch code will be made available upon paper acceptance at https://***/Labbeti/SSLH. © 2021, CC BY.

关键词： learning algorithms

Evaluating continual learning algorithms by generating 3D virtual environments

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Meloni, Enrico Betti, Alessandro Faggi, Lapo Marullo, Simone Tiezzi, Matteo Melacci, Stefano Dinfo University of Florence Diism University of Siena

Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating conditions for designing continuously evolving dynamics that are typical of the real-world. Many existing research works usually involve training and testing of virtual agents on datasets of static images or short videos, considering sequences of distinct learning tasks. However, in order to devise continual learning algorithms that operate in more realistic conditions, it is fundamental to gain access to rich, fully-customizable and controlled experimental playgrounds. Focussing on the specific case of vision, we thus propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially lifelong dynamic scenes with photo-realistic appearance. Scenes are composed of objects that move along variable routes with different and fully customizable timings, and randomness can also be included in their evolution. A novel element of this paper is that scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives. These general principles are concretely implemented exploiting a recently published 3D virtual environment. The user can generate scenes without the need of having strong skills in computer graphics, since all the generation facilities are exposed through a simple high-level Python interface. We publicly share the proposed generator. © 2021, CC BY-SA.

关键词： learning algorithms

On the practical consistency of meta-reinforcement learning algorithms

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xiong, Zheng Zintgraf, Luisa Beck, Jacob Vuorio, Risto Whiteson, Shimon Department of Computer Science University of Oxford United Kingdom

Consistency is the theoretical property of a meta learning algorithm that ensures that, under certain assumptions, it can adapt to any task at test time. An open question is whether and how theoretical consistency translates into practice, in comparison to inconsistent algorithms. In this paper, we empirically investigate this question on a set of representative meta-RL algorithms. We find that theoretically consistent algorithms can indeed usually adapt to out-of-distribution (OOD) tasks, while inconsistent ones cannot, although they can still fail in practice for reasons like poor exploration. We further find that theoretically inconsistent algorithms can be made consistent by continuing to update all agent components on the OOD tasks, and adapt as well or better than originally consistent ones. We conclude that theoretical consistency is indeed a desirable property, and inconsistent meta-RL algorithms can easily be made consistent to enjoy the same benefits. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

How much human-like visual experience do current self-supervised learning algorithms need in order to achieve human-level object recognition?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Orhan, Emin New York University United States

This paper addresses a fundamental question: how good are our current self-supervised visual representation learning algorithms relative to humans? More concretely, how much "human-like" natural visual experience would these algorithms need in order to reach human-level performance in a complex, realistic visual object recognition task such as ImageNet? Using a scaling experiment, here we estimate that the answer is several orders of magnitude longer than a human lifetime: typically on the order of a million to a billion years of natural visual experience (depending on the algorithm used). We obtain even larger estimates for achieving human-level performance in ImageNet-derived robustness benchmarks. The exact values of these estimates are sensitive to some underlying assumptions, however even in the most optimistic scenarios they remain orders of magnitude larger than a human lifetime. We discuss the main caveats surrounding our estimates and the implications of these surprising results. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms