检索结果-内蒙古大学图书馆

3rd IEEE asian conference on Innovation in Technology, asianCON 2023

ISBN: (纸本)9798350302288

The proceedings contain 326 papers. The topics discussed include: progressive web applications, a new way for faster testing of mobile application products;ThingSpeak based air pollution monitoring system using Raspberry Pi;combining CNN and SVM for accurate identification of ridge gourd leaf diseases;intelligent course scheduling system for college nursing teaching based on ant colony optimization algorithms;lung cancer detection using deep learning-based convolutional neural networks;data driven decision making algorithm for self-organizing networks by Q-learning methods for heterogeneous networks;improving facial recognition accuracy using local binary patterns;alternative methods of implementing the applications of smart home automation system;decentralized storage system to store data using blockchain technology;lane detection for self-driving cars using AI;and development of user friendly based home health monitoring system for the prediction of hypertension using machine learning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on machine learning, Image Processing, Network Security and Data Sciences, MIND 2021

3rd International Conference on Machine Learning, Image Proc...

引用

3rd International conference on machine learning, Image Processing, Network Security and Data Sciences, MIND 2021

ISBN: (纸本)9789811958670

The proceedings contain 68 papers. The special focus in this conference is on machine learning, Image Processing, Network Security and Data Sciences. The topics include: Analyzing Wearable Data for Diagnosing COVID-19 Using machine learning Model;comparative Analysis of Classification Methods to Predict Diabetes Mellitus on Noisy Data;a Robust Secure Access Entrance Method Based on Multi Model Biometric Credentials Iris and Finger Print;region Classification for Air Quality Estimation Using Deep learning and machine learning Approach;neuroevolution-Based Earthquake Intensity Classification for Onsite Earthquake Early Warning;detection of Credit Card Fraud by Applying Genetic Algorithm and Particle Swarm Optimization;traditional Indian Textile Designs Classification Using Transfer learning;classification of Electrocardiogram Signal Using Hybrid Deep learning Techniques;automated Detection of Type 2 Diabetes with Imbalanced and machine learning Methods;fault Diagnosis in Wind Turbine Blades Using machine learning Techniques;real-Time Detection of Vehicles on South asian Roads;stock Market Prediction Using Ensemble learning and Sentimental Analysis;Multiple Feature-Based Tomato Plant Leaf Disease Classification Using SVM Classifier;a Methodological Review of Time Series Forecasting with Deep learning Model: A Case Study on Electricity Load and Price Prediction;unexpected Alliance of Cardiovascular Diseases and Artificial Intelligence in Health Care;a Novel Smartphone-Based Human Activity Recognition Using Deep learning in Health care;An Enhanced Deep learning Approach for Smartphone-Based Human Activity Recognition in IoHT;classification of Indoor–Outdoor Scene Using Deep learning Techniques;prediction of the Reference Evapotranspiration Data from Raipur Weather Station in Chhattisgarh using Decision Tree-Based machine learning Techniques;deep Transfer learning and Intelligent Item Packing in Retail Management;preface.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games 15

Towards Human-Like RL: Taming Non-Naturalistic Behavior in D...

引用

15th asian conference on machine learning (acml)

作者： Ho, Kuo-Hao Hsieh, Ping-Chun Lin, Chiu-Chou Luo, You-Ren Wang, Feng-Jian Wu, I-Chen Natl Yang Ming Chiao Tung Univ Dept Comp Sci 1001 Daxue Rd Hsinchu Taiwan

In this paper, we propose a new approach called Adaptive Behavioral Costs in Reinforcement learning (ABC-RL) for training a human-like agent with competitive strength. While deep reinforcement learning agents have recently achieved superhuman performance in various video games, some of these unconstrained agents may exhibit actions, such as shaking and spinning, that are not typically observed in human behavior, resulting in peculiar gameplay experiences. To behave like humans and retain similar performance, ABC-RL augments behavioral limitations as cost signals in reinforcement learning with dynamically adjusted weights. Unlike traditional constrained policy optimization, we propose a new formulation that minimizes the behavioral costs subject to a constraint of the value function. By leveraging the augmented Lagrangian, our approach is an approximation of the Lagrangian adjustment, which handles the trade-off between the performance and the human-like behavior. Through experiments conducted on 3D games in DMLab-30 and Unity ML-Agents Toolkit, we demonstrate that ABC-RL achieves the same performance level while significantly reducing instances of shaking and spinning. These findings underscore the effectiveness of our proposed approach in promoting more natural and human-like behavior during gameplay.

关键词： Deep reinforcement learning Human-like agent Constrained policy optimization

来源：评论

学校读者我要写书评

暂无评论

Semantic Cross Attention for Few-shot learning 14

Semantic Cross Attention for Few-shot Learning

引用

asian conference on machine learning (acml)

作者： Xiao, Bin Liu, Chien-Liang Hsaio, Wen-Hoar Univ Ottawa Sch Elect Engn & Comp Sci 535 Legget Dr Kanata ON K2K 3B8 Canada Natl Yang Ming Chiao Tung Univ Dept Ind Engn & Management 1001 Univ Rd Hsinchu 30010 Taiwan Nanya Inst Technol Dept Comp Sci & Engn Taoyuan 32091 Taiwan Natl Chiao Tung Univ Hsinchu Taiwan

Few-shot learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and achieves promising results. FSL is characterized by using only a few images to train a model that can generalize to novel classes in image classification problems, but this setting makes it difficult to learn the visual features that can identify the images' appearance variations. The model training is likely to move in the wrong direction, as the images in an identical semantic class may have dissimilar appearances, whereas the images in different semantic classes may share a similar appearance. We argue that FSL can benefit from additional semantic features to learn discriminative feature representations. Thus, this study proposes a multi-task learning approach to view semantic features of label text as an auxiliary task to help boost the performance of the FSL task. Our proposed model uses word-embedding representations as semantic features to help train the embedding network and a semantic cross-attention module to bridge the semantic features into the typical visual modal. The proposed approach is simple, but produces excellent results. We apply our proposed approach to two previous metric-based FSL methods, all of which can substantially improve performance. The source code for our model is accessible from github (1).

关键词： Few-shot learning Multi-task learning Cross attention Metric-based method

来源：评论

学校读者我要写书评

暂无评论

Autonomous Ground Navigation in Highly Constrained Spaces: Lessons learned from The 3rd BARN Challenge at ICRA 2024

arXiv

引用

arXiv 2024年

作者： Xiao, Xuesu Xu, Zifan Datar, Aniket Warnell, Garrett Stone, Peter Damanik, Joshua Julian Jung, Jaewon Deresa, Chala Adane Huy, Than Duc Jinyu, Chen Yichen, Chen Cahyono, Joshua Adrian Wu, Jingda Mo, Longfei Lv, Mingyang Lan, Bowen Meng, Qingyang Tao, Weizhi Cheng, Li George Mason University United States The University of Texas Austin United States Army Research Laboratory United States Sony AI Japan Korea Republic of Singapore Hong Kong

The 3rd BARN (Benchmark Autonomous Robot Navigation) Challenge took place at the 2024 IEEE International conference on Robotics and Automation (ICRA 2024) in Yokohama, Japan and continued to evaluate the performance of state-of-the-art autonomous ground navigation systems in highly constrained environments. Similar to the trend in The 1st and 2nd BARN Challenge at ICRA 2022 and 2023 in Philadelphia (North America) and London (Europe), The 3rd BARN Challenge in Yokohama (Asia) became more regional, i.e., mostly asian teams participated. The size of the competition has slightly shrunk (six simulation teams, four of which were invited to the physical competition). The competition results, compared to last two years, suggest that the field has adopted new machine learning approaches while at the same time slightly converged to a few common practices. However, the regional nature of the physical participants suggests a challenge to promote wider participation all over the world and provide more resources to travel to the venue. In this article, we discuss the challenge, the approaches used by the three winning teams, and lessons learned to direct future research and competitions. © 2024, CC BY.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

Outbreak Prediction of COVID-19 3rd Wave in Asia 4th

Outbreak Prediction of COVID-19 3rd Wave in Asia

引用

4th International conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2021

作者： Sharma, Avinash Yadav, Dharminder Reen, L.S. Chandra, Umesh Mullana Haryana Ambala133207 India Department of Computer Science and Technology Glocal University UP Saharanpur India Seth Jai Parkash Institute of Information Technology Yamuna Nagar Haryana Radaur India Department Computer Science and Technology Banda University of Agriculture and Technology UP Banda India

ISBN: (纸本)9789811950360

Coronavirus is a pandemic for whole world and infected more than 200 countries of the world. Spreading of coronavirus started from china at the end of December and within three months, it infected whole world. Coronavirus is belonging to beta coronavirus family. Common symptoms of coronavirus are fever, dry cough, fatigue, and respiratory-related problem. This paper tries to study the infection rate of coronavirus in asian countries, rest of world countries, and overall world countries. Asia is largest continent of the world which contains approximate 50 countries and highest contributes in GDP. Population of asian countries 446.27 crore, that is 60 percentage of whole world population and covers 30 percent geographical area of world. China and India are the most populated countries in Asia. Total confirmed cases 2,056,051, recovered cases 502,045, and death cases 134,177 in the world. Scholar also divides the Asia continent into six regions such East, South, Central, North, Southeast and Western Asia for better understanding infection of coronavirus. This paper analyzes the confirmed cases, recovered cases, and death cases in Asia and understands the infection pattern date wise and countries wise. machine learning algorithm is used for prediction infection in the world and also predicts future infection rate and death rate in asian countries and world. Prophet is used for future prediction of confirmed and death cases in the asian countries. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

3rd asian conference on machine learning, acml 2011

3rd Asian Conference on Machine Learning, ACML 2011

引用

3rd asian conference on machine learning, acml 2011

The proceedings contain 23 papers. The topics discussed include: continuous rapid action value estimates;nonlinear online classification algorithm with probability margin;learning to locate relative outliers;microbagging estimators: an ensemble approach to distance-weighted classifiers;Bayesian inference for statistical abduction using Markov chain Monte Carlo;support vector machines under adversarial label noise;a general linear non-Gaussian state-space model: identifiability, identification, and applications;unsupervised multiple kernel learning;approximate model selection for large scale LSSVM;learning low-rank output kernels;learning rules from incomplete examples via implicit mention models;mixed-variate restricted Boltzmann machines;and computationally efficient sufficient dimension reduction via squared-loss mutual information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Mutual Information for Feature Selection in Programmatic Advertising

Using Mutual Information for Feature Selection in Programmat...

引用

IEEE International conference on INnovations in Intelligent SysTems and Applications (INISTA)

作者： Ciesielczyk, Michal Poznan Univ Tech Inst Control & Informat Engn Ul Piotrowo 3a PL-60965 Poznan Poland

ISBN: (纸本)9781509057955

Click-through rate estimation, the core task of programmatic display advertising, is associated with typical big data problems. Online algorithms for generalized linear models, such as Logistic Regression, are the most widely used data mining techniques for learning at such a massive scale. Since these models are unable to capture the underlying nonlinear data patterns, conjunction features are often introduced. This paper is focused on the problem of selecting the most informative 2nd and 3rd order conjunction features used in Logistic Regression. The performance of different feature selection methods based on mutual information is compared over a real-world dataset with over 10 million records. The empirical evaluation show the effectiveness of the proposed approach.

关键词： Big Data Mutual Information Feature Selection Logistic Regression Programmatic Advertising Click-through Rate Prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

第3届亚洲模式识别会议（英文）

引用

智能系统学报 2015年第3期10卷 453-453页

The 3rd IAPR asian conference on Pattern Recognition(ACPR2015),sponsored by the International Association of Pattern Recognition(IAPR)and supported by the Malaysian Image Analysis and machine Intelligence Association(MIAMI)and IEEE Computational Intelligence Society(CIS)Malaysia Chapter will be held on November 3-6,2015,Kuala Lumpur,*** First asian conference on Pattern Recognition(ACPR2011)was held at Beijing,China;while the second series(ACPR2013)was held at Okinawa,Japan.

关键词：第3届亚洲模式识别会议智能系统发展现状技术创新

来源：评论

学校读者我要写书评

暂无评论

Interactive learning from Unlabeled Instructions 30

Interactive Learning from Unlabeled Instructions

引用

30th conference on Uncertainty in Artificial Intelligence (UAI)

作者： Grizou, Jonathan Iturrate, Inaki Montesano, Luis Oudeyer, Pierre-Yves Lopes, Manuel Inria Bordeaux Sud Ouest Talence France Ecole Polytech Fed Lausanne CNBI Lausanne Switzerland Univ Zaragoza I3A Zaragoza Spain

ISBN: (纸本)9780974903910

Interactive learning deals with the problem of learning and solving tasks using human instructions. It is common in human-robot interaction, tutoring systems, and in human-computer interfaces such as brain-computer ones. In most cases, learning these tasks is possible because the signals are predefined or an ad-hoc calibration procedure allows to map signals to specific meanings. In this paper, we address the problem of simultaneously solving a task under human feedback and learning the associated meanings of the feedback signals. This has important practical application since the user can start controlling a device from scratch, without the need of an expert to define the meaning of signals or carrying out a calibration phase. The paper proposes an algorithm that simultaneously assign meanings to signals while solving a sequential task under the assumption that both, human and machine, share the same a priori on the possible instruction meanings and the possible tasks. Furthermore, we show using synthetic and real EEG data from a brain-computer interface that taking into account the uncertainty of the task and the signal is necessary for the machine to actively plan how to solve the task efficiently.

关键词： Brain computer interface

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：