检索结果-内蒙古大学图书馆

End-to-end dilated convolution network for document image semantic segmentation

Journal of Central South University 2021年第6期28卷 1765-1774页

作者： XU Can-hui SHI Cao CHEN Yi-nong School of Information Sciences and Technology Qingdao University of Science and TechnologyQingdao 266061China School of Computing Informatics and Decision Systems EngineeringArizona State UniversityTempeAZ 85287-8809USA

Semantic segmentation is a crucial step for document *** this paper,an NVIDIA Jetson Nano-based platform is applied for implementing semantic segmentation for teaching artificial intelligence concepts and *** extract semantic structures from document images,we present an end-to-end dilated convolution network *** convolutions have well-known advantages for extracting multi-scale context information without losing spatial *** model utilizes dilated convolutions with residual network to represent the image features and predicting pixel *** convolution part works as feature extractor to obtain multidimensional and hierarchical image *** consecutive deconvolution is used for producing full resolution segmentation *** probability of each pixel decides its predefined semantic class *** understand segmentation granularity,we compare performances at three different *** fine grained class to coarse class levels,the proposed dilated convolution network architecture is evaluated on three document *** experimental results have shown that both semantic data distribution imbalance and network depth are import factors that influence the document’s semantic segmentation *** research is aimed at offering an education resource for teaching artificial intelligence concepts and techniques.

关键词： semantic segmentation document images deep learning NVIDIA jetson nano

来源：评论

学校读者我要写书评

暂无评论

Graph Learning: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第2期2卷 109-127页

作者： Xia, Feng Sun, Ke Yu, Shuo Aziz, Abdul Wan, Liangtian Pan, Shirui Liu, Huan School of Engineering IT and Physical Sciences Federation University Australia BallaratVIC3353 Australia School of Software Dalian University of Technology Dalian116620 China Faculty of Information Technology Monash University MelbourneVIC3800 Australia School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in differe

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Technologies Supporting Artificial Intelligence and Robotics Application Development

引用

Journal of Artificial Intelligence and Technology 2021年第1期1卷 1-8页

作者： Yinong Chen Gennaro De Luca School of Computing Informaticsand Decision Systems EngineeringArizona State UniversityTempeAZ 85287USA Faculty Ambassador Amazon Web Services at ASUTempeAZ 85287USA Polytechnic School Arizona State UniversityMesaAZ 85212USA

Artificial intelligence(AI)and robotics have gone through three generations of development,from Turing test,logic theory machine,to expert system and self-driving *** the third-generation today,AI and robotics have collaboratively been used in many areas in our society,including industry,business,manufacture,research,and *** are many challenging problems in developing AI and robotics *** launch this new Journal of Artificial Intelligence and Technology to facilitate the exchange of the latest research and practice in AI and *** this inaugural issue,we first introduce a few key technologies and platforms supporting the third-generation AI and robotics application development based on stacks of technologies and *** present examples of such development environments created by both industry and *** also selected eight papers in the related areas to celebrate the foundation of this journal.

关键词： artificial intelligence robotics machine learning education

来源：评论

学校读者我要写书评

暂无评论

Intelligent Voice Instructor-Assistant System for Collaborative and Interactive Classes

引用

Journal of Artificial Intelligence and Technology 2021年第2期1卷 121-130页

作者： Matthew Baker Xiaohui Hu Gennaro De Luca and Yinong Chen School of Computing Informatics and Decision Systems EngineeringArizona State UniversityTempeAZ 85281 USA School of Physics and Telecommunication Engineering South China Normal UniversityGuangzhouGuangdong 510006 China Polytechnic School Arizona State UniversityMesaAZ 85212 USA

College classes are becoming increasingly large.A critical component in scaling class size is the collaboration and interactions among instructors,teaching assistants,and *** develop a prototype of an intelligent voice instructorassistant system for supporting large classes,in which Amazon Web Services,Alexa Voice Services,and self-developed services are *** uses a scraping service for reading the questions and answers from the past and current course discussion boards,organizes the questions in JavaScript object notation format,and stores them in the database,which can be accessed by Amazon web services Alexa *** a voice question from a student comes,Alexa is used for translating the voice sentence into ***,Siamese deep long short-term memory model is introduced to calculate the similarity between the question asked and the questions in the database to find the best-matched *** with no match will be sent to the instructor,and instructor’s answer will be added into the *** show that the implemented model achieves promising results that can lead to a practical *** voice instructor-assistant system starts with a small set of *** can grow through learning and improving when more and more questions are asked and answered.

关键词： natural language processing voice processing machine learning Long short-term memory(LSTM)network questions and answers

来源：评论

学校读者我要写书评

暂无评论

Evaluation Methods and Measures for Causal Learning Algorithms

arXiv

引用

arXiv 2022年

作者： Cheng, Lu Guo, Ruocheng Moraffah, Raha Sheth, Paras Candan, K. Selçuk Liu, Huan School of Data Science City University of Hong Kong China School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

The convenient access to copious multi-faceted data has encouraged machine learning researchers to reconsider correlation-based learning and embrace the opportunity of causality-based learning, i.e., causal machine learning (causal learning). Recent years have therefore witnessed great effort in developing causal learning algorithms aiming to help AI achieve human-level intelligence. Due to the lack-of ground-truth data, one of the biggest challenges in current causal learning research is algorithm evaluations. This largely impedes the cross-pollination of AI and causal inference, and hinders the two fields to benefit from the advances of the other. To bridge from conventional causal inference (i.e., based on statistical methods) to causal learning with big data (i.e., the intersection of causal inference and machine learning), in this survey, we review commonly-used datasets, evaluation methods, and measures for causal learning using an evaluation pipeline similar to conventional machine learning. We focus on the two fundamental causal-inference tasks and causality-aware machine learning tasks. Limitations of current evaluation procedures are also discussed. We then examine popular causal inference tools/packages and conclude with primary challenges and opportunities for benchmarking causal learning algorithms in the era of big data. The survey seeks to bring to the forefront the urgency of developing publicly available benchmarks and consensus-building standards for causal learning evaluation with observational data. In doing so, we hope to broaden the discussions and facilitate collaboration to advance the innovation and application of causal learning. Impact Statement—Causal learning goes beyond machine learning due to its power of uncovering data generating processes. Causality relates to crucial open problems in machine learning. On the opposite, machine learning contributes to addressing fundamental challenges in causal inference. One key challenge of causal

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Measuring Time-Constrained Influence to Predict Adoption in Online Social Networks

引用

ACM Transactions on Social computing 2020年第3期3卷 1–26页

作者： Marin, Ericsson Guo, Ruocheng Shakarian, Paulo School of Computing Informatics and Decision Systems Engineering Arizona State University 699 S Mill Ave TempeAZ85281 United States

Recently, there has been strong interest in measuring influence in online social networks. Different measures have been proposed to predict when individuals will adopt a new behavior, given the influence produced by their friends. In this article, we show that one can achieve significant improvement over these measures, extending them to consider a pair of time constraints that provide a better proxy for social influence. By conducting an engineering study that investigates retweet networks from Twitter and Sina Weibo datasets, we tune those two parameters while we examine the correlation between influence and the probability of adoption, as well as the ability to predict adoption, estimating the real susceptibility and influence to which microblog users are dynamically subjected. Although there are limitations about using retweets to analyze social influence, our results show that for the simple count of active neighbors, its correlation with the probability of adoption is boosted up to 518.75%, whereas similar gains are observed for the other influence measures analyzed. We also obtain up to 18.89% improvement in F1 score when compared to recent machine learning techniques that aim to predict adoption, enabling practical use of the corresponding concepts for social influence applications. © 2020 ACM.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Convolutional Bayesian Models for Anatomical Landmarking on Multi-dimensional Shapes 23rd

Convolutional Bayesian Models for Anatomical Landmarking on ...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Fan, Yonghui Wang, Yalin School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

ISBN: (纸本)9783030597184

The anatomical landmarking on statistical shape models is widely used in structural and morphometric analyses. The current study focuses on leveraging geometric features to realize an automatic and reliable landmarking. The existing implementations usually rely on classical geometric features and data-driven learning methods. However, such designs often have limitations to specific shape types. Additionally, calculating the features as a standalone step increases the computational cost. In this paper, we propose a convolutional Bayesian model for anatomical landmarking on multi-dimensional shapes. The main idea is to embed the convolutional filtering in a stationary kernel so that the geometric features are efficiently captured and implicitly encoded into the prior knowledge of a Gaussian process. In this way, the posterior inference is geometrically meaningful without entangling with extra features. By using a Gaussian process regression framework and the active learning strategy, our method is flexible and efficient in extracting arbitrary numbers of landmarks. We demonstrate extensive applications on various publicly available datasets, including one brain imaging cohort and three skeletal anatomy datasets. Both the visual and numerical evaluations verify the effectiveness of our method in extracting significant landmarks. © 2020, Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Action language BC+

Action language BC+

引用

作者： Babb, Joseph Lee, Joohyung School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States

Action languages are formal models of parts of natural language that are designed to describe effects of actions. Many of these languages can be viewed as high-level notations of answer set programs structured to represent transition systems. However, the form of answer set programs considered in the earlier work is quite limited in comparison with the modern Answer Set Programming (ASP) language, which allows several useful constructs for knowledge representation, such as choice rules, aggregates and abstract constraint atoms. We propose a new action language called BC +, which closes the gap between action languages and the modern ASP language. The main idea is to define the semantics of BC + in terms of general stable model semantics for propositional formulas, under which many modern ASP language constructs can be identified with shorthands for propositional formulas. Language BC + turns out to be sufficiently expressive to encompass the best features of other actionlanguages, such as languages B, C, C + and BC. Computational methods available in ASP solvers are readily applicable to compute BC +, which led to an implementation of the language by extending system cplus2asp. © 2015 The Author. Published by Oxford University Press. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Order Matters: Generating Progressive Explanations for Planning Tasks in Human-Robot Teaming

Order Matters: Generating Progressive Explanations for Plann...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mehrdad Zakershahrak Shashank Rao Marpally Akshay Sharma Ze Gong Yu Zhang School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe AZ

Prior work on generating explanations in a planning context has focused on providing the rationale behind an AI agent’s decision-making. While these methods offer the right explanations, they fail to heed the cognitive requirement of understanding an explanation from the explainee or human’s perspective. In this work, we set out to address this issue by considering the order for communicating information in an explanation, or the progressiveness of making explanations. Progression is the notion of building complex concepts on simpler ones, which is known to benefit learning. In this work, we investigate a similar effect when an explanation is composed of multiple parts that are communicated sequentially. The challenge here lies in determining the order for receiving different parts of an explanation that would assist in understanding. Given the sequential nature, a formulation based on goal-based MDP is presented. The reward function of this MDP is learned via inverse reinforcement learning based on training data. We evaluated our approach in an escape-room domain to demonstrate its effectiveness. Upon analyzing the results, it revealed that the desired order arises strongly from both domain-dependent and independence features. This result confirmed our expectation that the process of understanding an explanation for planning tasks was progressive and context dependent. We also showed that the explanations generated using the learned rewards achieved better task performance and simultaneously reduced cognitive load. These results shed light on designing explainable robots across various domains.

关键词： Automation Conferences decision making Buildings Training data Reinforcement learning Planning

来源：评论

学校读者我要写书评

暂无评论

Improving Batch Normalization with Skewness Reduction for Deep Neural Networks

Improving Batch Normalization with Skewness Reduction for De...

引用

International Conference on Pattern Recognition

作者： Pak Lun Kevin Ding Sarah Martin Baoxin Li School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe AZ

Batch Normalization (BN) is a well-known technique used in training deep neural networks. The main idea behind batch normalization is to normalize the features of the layers (i.e., transforming them to have a mean equal to zero and a variance equal to one). Such a procedure encourages the optimization landscape of the loss function to be smoother, and improves the learning of the networks for both speed and performance. In this paper, we demonstrate that the performance of the network can be improved, if the distributions of the features of the output in the same layer are similar. As normalizing based on mean and variance does not necessarily make the features to have the same distribution, we propose a new normalization scheme: Batch Normalization with Skewness Reduction (BNSR). Comparing with other normalization approaches, BNSR transforms not just only the mean and variance, but also the skewness of the data. By tackling this property of a distribution, we are able to make the output distributions of the layers to be further similar. The nonlinearity of BNSR may further improve the expressiveness of the underlying network. Comparisons with other normalization schemes are tested on the CIFAR-100 and ImageNet datasets. Experimental results show that the proposed approach can outperform other state-of-the-arts that are not equipped with BNSR.

关键词： Training Neural networks Transforms Pattern recognition Optimization

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：