检索结果-内蒙古大学图书馆

2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020

作者： Jensen, T.P. Tata, S. Ijspeert, A.J. Tolu, S. Automation and Control Department of Electrical Engineering Technical University of Denmark Kgs. Lyngby Denmark Biorobotics Laboratory School of Engineering École Polytechnique Fédérale de Lausanne Lausanne Switzerland

ISBN: (纸本)9781450361231

Human beings and other vertebrates show remarkable performance and efficiency in locomotion, but the functioning of their biological control systems for locomotion is still only partially understood. The basic patterns and timing for locomotion are provided by a central pattern generator (CPG) in the spinal cord. The cerebellum is known to play an important role in adaptive locomotion. Recent studies have given insights into the error signals responsible for driving the cerebellar adaptation in locomotion. However, the question of how the cerebellar output influences the gait remains unanswered. We hypothesize that the cerebellar correction is applied to the pattern formation part of the CPG. Here, a bio-inspired control system for adaptive locomotion of the musculoskeletal system of the mouse is presented, where a cerebellar-like module adapts the step time by using the double support interlimb asymmetry as a temporal teaching signal. The control system is tested on a simulated mouse in a split-belt treadmill setup similar to those used in experiments with real mice. The results show adaptive locomotion behavior in the interlimb parameters similar to that seen in humans and mice. The control system adaptively decreases the double support asymmetry that occurs due to environmental perturbations in the split-belt protocol. © 2020 ACM.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization based variable learning factor least mean square algorithm to control DVR in infected grid systems 9

Optimization based variable learning factor least mean squar...

引用

9th IEEE International Conference on Power Electronics, Drives and Energy Systems, PEDES 2020

作者： Naidu, Talada Appala Al-Durra, Ahmed El-Fouly, Tarek H. M. Zeineldin, Hatem Advanced Power Energy Centre Khalifa University EECS Department Abu Dhabi127788 United Arab Emirates

ISBN: (纸本)9781728156729

In this paper, a variable learning rate least mean square control algorithm has been proposed to control Dynamic Voltage Restorer for compensating the disturbances present in the supply source side of a distribution network. The proposed control algorithm is equipped with an optimization algorithm based on Slime Mould for the tuning of PI controller gains. The topology of the Dynamic Voltage Restorer presented in this paper is a voltage source converter with capacitor as an energy storage device that is utilized for the compensation of four various disturbances in the supply voltage viz. voltage sag, voltage swell, unbalance, and voltage distortions. System performance has been validated via simulation using MATLAB/Simulink. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Image Quality Evaluation Method of Depth learning Model Based on Core Concept 5

Research on Image Quality Evaluation Method of Depth Learnin...

引用

2020 5th International Conference on Intelligent Computing and Signal Processing, ICSP 2020

作者： Huang, Wen Wang, Juan School of Cyberspace Security Chengdu University of Information Technology Chengdu610225 China

In view of the fact that the existing image quality evaluation methods are generally artificial design features, it is difficult to automatically and effectively extract image features that conform to the human visual system. Inspired by human visual characteristics, a new full reference image quality evaluation method based on depth learning model based on core concepts is proposed. Firstly, depth learning algorithm is used to extract multi-layer features from reference images and distorted images respectively. Then, the local similarity of the feature map of the reference image and the distorted image in each layer is calculated as the local quality description of the corresponding depth. Finally, the local quality of all layers is synthesized to obtain the overall quality score of the image. On the basis of the pre-training model, the depth model network is fine-tuned by using the image visual evaluation data set to obtain a depth model for evaluation. The standard experiment shows that fine-tuning training of each pre-training model on the standard data set achieves good classification results. Experiments show that the designed depth learning model based on core concepts is superior to the existing full reference image quality evaluation methods, and its prediction results have good accuracy and consistency with subjective quality evaluation. © 2019 Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Expert-guided machine-learning for well location optimization under subsurface uncertainty 1

Expert-guided machine-learning for well location optimizatio...

引用

1st EAGE Digitalization Conference and Exhibition

作者： Schulze-Riegert, R. Lang, P. Pongtepupathum, W. Drew, C. Schlumberger Norwegian Technology Center Norway Schlumberger Abingdon Technology Center United Kingdom

This work investigates the application of an expert-guided machine learning technique for identification of connected and high saturated oil volumes for optimal well placement. The technique is designed to work on property maps of a single model as well as ensembles of reservoir models for robust field development optimization under subsurface uncertainty. The methodology is embedded into a structured workflow design for improving a baseline well location design of the Olympus reservoir model ensemble, a public benchmark project for field development optimization under uncertainty. This work suggests an iterative improvement of well location designs using probabilistic well ranking to identify low performing wells, probability maps to understand reservoir performance and analytics-based optimization steps targeting large connected and high saturated oil volumes. The methodology is described, and application results are presented for a full optimization loop. The structured approach highlights the value of novel learning techniques to provide an efficient and manageable solution for optimizing a well location design under subsurface uncertainty. © EAGE 2019.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A bandit learning algorithm and applications to auction design 34

A bandit learning algorithm and applications to auction desi...

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Thng, Nguyn Kim IBISC Univ. Evry University Paris-Saclay France

We consider online bandit learning in which at every time step, an algorithm has to make a decision and then observe only its reward. The goal is to design efficient (polynomial-time) algorithms that achieve a total reward approximately close to that of the best fixed decision in hindsight. In this paper, we introduce a new notion of (?, µ)-concave functions and present a bandit learning algorithm that achieves a performance guarantee which is characterized as a function of the concavity parameters ? and µ. The algorithm is based on the mirror descent algorithm in which the update directions follow the gradient of the multilinear extensions of the reward functions. The regret bound induced by our algorithm is Oe(vT) which is nearly optimal. We apply our algorithm to auction design, specifically to welfare maximization, revenue maximization, and no-envy learning in auctions. In welfare maximization, we show that a version of fictitious play in smooth auctions guarantees a competitive regret bound which is determined by the smooth parameters. In revenue maximization, we consider the simultaneous second-price auctions with reserve prices in multi-parameter environments. We give a bandit algorithm which achieves the total revenue at least 1/2 times that of the best fixed reserve prices in hindsight. In no-envy learning, we study the bandit item selection problem where the player valuation is submodular and provide an efficient 1/2-approximation no-envy algorithm. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Machine learning and Deep learning Techniques for Cybersecurity: A Review 1st

Machine Learning and Deep Learning Techniques for Cybersecur...

引用

1st International Conference on Artificial Intelligence and Computer Visions, AICV 2020

作者： Salloum, Said A. Alshurideh, Muhammad Elnagar, Ashraf Shaalan, Khaled Research Institute of Sciences and Engineering University of Sharjah Sharjah United Arab Emirates Faculty of Engineering and IT The British University in Dubai Dubai United Arab Emirates Faculty of Business University of Jordan Amman Jordan Management Department University of Sharjah Sharjah United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9783030442880

In this review, significant literature surveys on machine learning (ML) and deep learning (DL) techniques for network analysis of intrusion detection are explained. In addition, it presents a short tutorial explanation on every ML/DL method. Data holds a significant position in ML/DL methods;hence this paper highlights the datasets used in machine learning techniques, which are the primary tools for analyzing network traffic and detecting abnormalities. In addition, we elaborate on the issues faced in using ML/DL for cybersecurity and offer recommendations for future studies. © 2020, Springer Nature Switzerland AG.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

learning interpretable models in the property specification language 29

Learning interpretable models in the property specification ...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Roy, Rajarshi Fisman, Dana Neider, Daniel Max Planck Institute for Software Systems Kaiserslautern Germany Ben-Gurion University Be'er Sheva Israel

ISBN: (纸本)9780999241165

We address the problem of learning human-interpretable descriptions of a complex system from a finite set of positive and negative examples of its behavior. In contrast to most of the recent work in this area, which focuses on descriptions expressed in Linear Temporal Logic (LTL), we develop a learning algorithm for formulas in the IEEE standard temporal logic: Property Specification Language (PSL). Our work is motivated by the fact that many natural properties, such as an event happening at every n-th point in time, cannot be expressed in LTL, whereas it is easy to express such properties in PSL. Moreover, formulas in PSL can be more succinct and easier to interpret (due to the use of regular expressions in PSL formulas) than formulas in LTL. The learning algorithm we designed, builds on a framework recently proposed for learning LTL formulas. Roughly speaking, our algorithm reduces the learning task to a constraint satisfaction problem in propositional logic and uses a SAT solver to search for a solution. We have implemented our algorithm and performed a comparative study between the proposed method and the existing LTL learning algorithm. Our results illustrate the effectiveness of the proposed approach to provide succinct human-interpretable descriptions from examples. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Population cross learning algorithm combining greedy search for community detection 4

Population cross learning algorithm combining greedy search ...

引用

2020 4th International Conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2020

作者： Wang, Xiaogang Yan, Guanghui Li, Shikui Zhou, Ning School of Electronic and Information Engineering Lanzhou Jiaotong University Lanzhou730070 China

In order to improve the precision of modularity optimization and community detection, this paper presented a complex network community detection algorithm based on cross learning among individuals of population combining greedy search. Individuals' codes indicated community partition. Individuals comparatively studied with each other to spread good genes and optimize modularity fast. Besides, aiming at improving the algorithm, the best communities, where some randomly selected nodes will move in, would be found by using greedy search maximizing the local modularity increment. The algorithm was tested on artificial networks and some typical real networks, compared with some typical algorithms. The results show that algorithm can get convergence quickly, achieve better modularity value, and finely detect and identify community structures. © Published under licence by IOP Publishing Ltd.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method of Casting Defects Detection Based on Deep learning

An Efficient Method of Casting Defects Detection Based on De...

引用

2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications, AEECA 2020

作者： Xue, Lin Hei, Junming Chen, Xiangji Xu, Ying Zheng, Licai Dalian University of Technology School of Mechanical Engineering Dalian China Sanying Precision Instruments Co. Ltd Tianjin China

ISBN: (纸本)9781728165202

Casting defects detection is necessary for manufacturing industry. In this paper, we propose a casting defects detection method based on the Deep learning algorithm. We aims at solving problems of insufficient computing resources in most manufacturing enterprises, and we introduce the Efficientnet network and depth separable convolution to saving computing resources while maintaining detection accuracy. The experiment results verifies our method could perform well even if in the case of insufficient computing resources. It provides a automated casting defects detection method and give a proposal to the industrial defect detection researchers who faced the problem about computing resources. © 2020 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Noise-Tolerant Coreset-Based Class Incremental Continual learning

arXiv

引用

arXiv 2025年

作者： Mucllari, Edison Raghavan, Aswin Daniels, Zachary Alan University of Kentucky LexingtonKY United States SRI International PrincetonNJ United States

Many applications of computer vision require the ability to adapt to novel data distributions after deployment. Adaptation requires algorithms capable of continual learning (CL). Continual learners must be plastic to adapt to novel tasks while minimizing forgetting of previous tasks. However, CL opens up avenues for noise to enter the training pipeline and disrupt the CL. This work focuses on label noise and instance noise in the context of class-incremental learning (CIL), where new classes are added to a classifier over time, and there is no access to external data from past classes. We aim to understand the sensitivity of CL methods that work by replaying items from a memory constructed using the idea of Coresets. We derive a new bound for the robustness of such a method to uncorrelated instance noise under a general additive noise threat model, revealing several insights. Putting the theory into practice, we create two continual learning algorithms to construct noise-tolerant replay buffers. We empirically compare the effectiveness of prior memory-based continual learners and the proposed algorithms under label and uncorrelated instance noise on five diverse datasets. We show that existing memory-based CL are not robust whereas the proposed methods exhibit significant improvements in maximizing classification accuracy and minimizing forgetting in the noisy CIL setting. © 2025, CC BY-NC-SA.

关键词： learning algorithms

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：