检索结果-内蒙古大学图书馆

IEEE 16th International Conference on cognitive Informatics and cognitive Computing (ICCI*CC)

作者： Valipour, Mehrdad Wang, Yingxu Univ Calgary Int Inst Cognit Informat & Cognit Comp ICIC Lab Computat Intelligence Cognit Syst Denotat Mat Dept Elect & Comp EngnSchulich Sch Engn 2500 Univ Dr NW Calgary AB T2N 1N4 Canada Univ Calgary Hotchkiss Brain Inst 2500 Univ Dr NW Calgary AB T2N 1N4 Canada

ISBN: (纸本)9781538607718

Semantic comprehension is a fundamental challenge to machine learning. A methodology for building quantitative semantic hierarchies of formal concepts is formally described by cognitive machine learning. The algorithm of concept semantic hierarchy learning (CSH_learning) is developed based on a set of semantic analysis and synthesis rules according to concept algebra. The algorithm and rules are applied in quantitative determination of levels of arbitrary concepts for the semantic hierarchy of a machines' cognitive knowledge bases. Experiments on 600+ formal concepts indicate the effectiveness of the algorithm for a wide range of applications including cognitive language processing, semantic analyses, cognitive machine learning, cognitive computation and computational linguistics.

关键词： cognitive machine learning concept algebra semantic analysis semantic synthesis semantic hierarchy cognitive algorithm cognitive computation

来源：评论

学校读者我要写书评

暂无评论

Formal Concept Refinement by Deep cognitive machine learning 16

Formal Concept Refinement by Deep Cognitive Machine Learning

引用

IEEE 16th International Conference on cognitive Informatics and cognitive Computing (ICCI*CC)

作者： Zatarain, Omar A. Wang, Yingxu Univ Calgary Int Inst Cognit Informat & Cognit Comp ICIC Lab Computat Intelligence Cognit Syst Denotat Mat Dept Elect & Comp EngnSchulich Sch Engn 2500 Univ Dr NW Calgary AB T2N 1N4 Canada Univ Calgary Hotchkiss Brain Inst 2500 Univ Dr NW Calgary AB T2N 1N4 Canada

ISBN: (纸本)9781538607718

Concept generation and refinement is a process to generate and improve machine's knowledge base represented by a comprehensive set of formal concepts. An unsupervised algorithm for concept refinement is developed for autonomously upgrading and enhancing acquired concepts of knowledge in a cognitive knowledge base built by cognitive robots and systems. The concept refinement algorithm is implemented based on a set of rules of concept algebra and semantic analyses. Experimental results demonstrate that cognitive machines can autonomously refine their knowledge by improving acquired concepts in a dynamic process mimicking human learning mechanisms in deep machine learning and cognitive computing.

关键词： cognitive machine learning concept refinement algorithm unsupervised learning knowledge learning computational linguistics cognitive computation

来源：评论

学校读者我要写书评

暂无评论

Algorithms for Determining Semantic Relations of Formal Concepts by cognitive machine learning based on Concept Algebra 15

Algorithms for Determining Semantic Relations of Formal Conc...

引用

15th IEEE International Conference on cognitive Informatics and cognitive Computing (ICCI*CC)

作者： Valipour, Mehrdad Wang, Yingxu Zatarain, Omar A. Gavrilova, Marina L. Univ Calgary Int Inst Cognit Informat & Cognit Comp ICIC Lab Computat Intelligence Denotat Math Software S Dept Elect & Comp EngnSchulich Sch Engn 2500 Univ Dr NW Calgary AB T2N 1N4 Canada Univ Calgary Hotchkiss Brain Inst 2500 Univ Dr NW Calgary AB T2N 1N4 Canada Stanford Univ Packard Dept Elect Engn Informat Syst Lab Stanford CA 94305 USA

ISBN: (纸本)9781509038466

It is recognized that the semantic space of knowledge is a hierarchical concept network. This paper presents theories and algorithms of hierarchical concept classification by quantitative semantic relations via machine learning based on concept algebra. The equivalence between formal concepts are analyzed by an Algorithm of Concept Equivalence Analysis (ACEA), which quantitatively determines the semantic similarity of an arbitrary pair of formal concepts. This leads to the development of the Algorithm of Relational Semantic Classification (ARSC) for hierarchically classify any given concept in the semantic space of knowledge. Experiments applying Algorithms ACEA and ARSC on 20 formal concepts are successfully conducted, which encouragingly demonstrate the deep machine understanding of semantic relations and their quantitative weights beyond human perspectives on knowledge learning and natural language processing.

关键词： cognitive machine learning formal concept cognitive algorithms concept algebra semantic analysis concept classification concept hierarchy concept similarity knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Formal Rules for Concept and Semantics Manipulations in cognitive Linguistics and machine learning 16

Formal Rules for Concept and Semantics Manipulations in Cogn...

引用

IEEE 16th International Conference on cognitive Informatics and cognitive Computing (ICCI*CC)

作者： Wang, Yingxu Univ Calgary Schulich Sch Engn Int Inst Cognit Informat & Cognit Comp ICIC Dept Elect & Comp Engn 2500 Univ Dr NW Calgary AB T2N 1N4 Canada Univ Calgary Hotchkiss Brain Inst 2500 Univ Dr NW Calgary AB T2N 1N4 Canada

ISBN: (纸本)9781538607718

Formal semantic theories underpin a wide range of methodologies in knowledge science, cognitive linguistics, machine learning, and cognitive computing. This paper presents a set of mathematical rules for rigorous concept and semantics manipulations. Mathematical models of the universe of discourse of knowledge, semantic space and formal concepts are created. The formal properties of knowledge are elaborated in the categories of intension/extension, semantic and hierarchical rules based on concept algebra. Recent experiments and breakthroughs in cognitive systems of machine knowledge learning demonstrate applications of the fundamental theories for cognitive linguistics and brain-inspired machine learning.

关键词： Formal semantics cognitive linguistics cognitive computing concept algebra semantic algebra knowledge science cognitive machine learning knowledge learning cognitive robot AI computational intelligence cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Usage of machine learning and Monte Carlo Method as Probabilistic Hybrid Tool to Predict Next Pandemic

Usage of Machine Learning and Monte Carlo Method as Probabil...

引用

2023 IEEE International Conference on Electrical, Computer and Energy Technologies, ICECET 2023

作者： Nieto-Chaupis, Huber Universidad Autónoma Del Perú Panamericana Sur Km.16.3 Villa el Salvador Lima Peru

ISBN: (纸本)9798350327816

This paper explores the scenarios where the combination of algorithms based at machine learning with Monte Carlo method can be advantageous to assess the next pandemic. Thus, taking into account the experience of Covid-19, and the design of strategies that have served to alleviate the crisis cause by the spreading of Corona virus, in this paper a general algorithm is proposed. Essentially the proposal takes into account the gathered statistics along the years 2020-2021-2022 so that it constitutes a pattern that might be perceived again in next pandemics. In concrete, this work aims to present simulations taking as input the data of Covid-19. Special attention is paid on the initial period. It is because it was observed similar patterns in most countries that have reported a fast propagation of virus. Thus the MItchell's criteria are employed to identify the beginning of pandemic as well as the Monte Carlo method is also used in order to accept potential realistic events of pandemic, whereas the ones that turned out to be inconsistent to Covid-19 data and patterns of propagation are rejected. From the results, a discussion about the validity of this study is finally given. © 2023 IEEE.

关键词： cognitive machine learning Covid-19

来源：评论

学校读者我要写书评

暂无评论

An optimized cognitive-assisted machine translation approach for natural language processing

引用

COMPUTING 2020年第3期102卷 605-622页

作者： Alarifi, Abdulaziz Alwadain, Ayed King Saud Univ Community Coll Comp Sci Dept Riyadh 11437 Saudi Arabia

Currently, computer-aided machine translation (MT) processes play a significant role in natural language processing used to translate a specified language into another language like English to Spanish, Latin to French. During the translation process, and particularly during phrase composition, MT systems may exhibit several issues, including failure to produce high quality translations, increased time consumption, diminished linguistic precision and complexity. This research introduces an optimized cognitive assisted statistical MT process that is intended to reduce these difficulties. This process uses a supervised machine learning technique (OCSMT-SMT) for natural language processing that is intended to translate phrases with a higher degree of precision than other Support Vector machine, Linear Regression, Decision Trees, Naive Bayes, and K-Nearest Neighbor MT techniques. The method introduced here uses semantic operations to examine the collected messages that are processed in network and obtained results have been stored in the memory to get the exact translation which helps to learn phrase semantics using MT. The OCSMT-SMT approach enables smarter, faster decision making regarding phrase translations, which greatly reduces translation time. The efficiency of this approach is evaluated using the bilingual evaluation understudy (BLEU) and Better Evaluation as Ranking (BEER) metrics for English language phrase datasets in English language. This ensures the high precision while performing the MT process.

关键词： Computer aided machine translation cognitive assisted statistical machine translation BLEU BEER cognitive machine learning

来源：评论

学校读者我要写书评

暂无评论

How Do Humans Access the Credibility of Weblogs: Qualifying and Verifying Human Factors with machine learning

How Do Humans Access the Credibility of Weblogs: Qualifying ...

引用

CHI Conference on Human Factors in Computing Systems (CHI)

作者： Jo, Yonggeol Kim, Minwoo Han, Kyungsik Ajou Univ Suwon South Korea

ISBN: (纸本)9781450359702

The purpose of this paper is to understand the factors involved when a human judges the credibility of information and to develop a classification model for weblogs, a primary source of information for many people. Considering both computational and human-centered approaches, we conducted a user study designed to consider two cognitive procedures-(1) visceral, behavioral and (2) reflective assessments-in the evaluation of information credibility. The results of the 80-participant study highlight that human cognitive processing varies according to an individual's purpose and that humans consider the structures and styles of content in their reflective assessments. We experimentally proved these findings through the development and analysis of classification models using 16,304 real blog posts written by 2,944 bloggers. Our models yield greater accuracy and efficiency than the models with well-known best features identified in prior research.

关键词： Information credibility Weblogs Social networking services cognitive machine learning

来源：评论

学校读者我要写书评

暂无评论

How Do Humans Assess the Credibility on Web Blogs: Qualifying and Verifying Human Factors with machine learning 19

How Do Humans Assess the Credibility on Web Blogs: Qualifyin...

引用

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

作者： Yonggeol Jo Minwoo Kim Kyungsik Han Ajou University Suwon Republic of Korea

ISBN: (纸本)9781450359702

The purpose of this paper is to understand the factors involved when a human judges the credibility of information and to develop a classification model for weblogs, a primary source of information for many people. Considering both computational and human-centered approaches, we conducted a user study designed to consider two cognitive procedures--(1) visceral, behavioral and (2) reflective assessments--in the evaluation of information credibility. The results of the 80-participant study highlight that human cognitive processing varies according to an individual's purpose and that humans consider the structures and styles of content in their reflective assessments. We experimentally proved these findings through the development and analysis of classification models using 16,304 real blog posts written by 2,944 bloggers. Our models yield greater accuracy and efficiency than the models with well-known best features identified in prior research

关键词： cognitive machine learning

来源：评论

学校读者我要写书评

暂无评论

cognitive Modeling of Polymorphic Malware Using Fractal Based Semantic Characterization

Cognitive Modeling of Polymorphic Malware Using Fractal Base...

引用

IEEE International Symposium on Technologies for Homeland Security (HST)

作者： Khan, Muhammad Salman Siddiqui, Sana Ferens, Ken Univ Manitoba Dept Elect & Comp Engn EITC Winnipeg MB R3T 5V6 Canada

ISBN: (纸本)9781509063567

Polymorphic malware belong to the class of host based threats which defy signature based detection mechanisms. Threat actors use various code obfuscation methods to hide the code details of the polymorphic malware and each dynamic iteration of the malware bears different and new signatures therefore makes its detection harder by signature based antimalware programs. Sandbox based detection systems perform syntactic analysis of the binary files to find known patterns from the un-encrypted segment of the malware file. Anomaly based detection systems can detect polymorphic threats but generate enormous false alarms. In this work, authors present a novel cognitive framework using semantic features to detect the presence of polymorphic malware inside a Microsoft Windows host using a process tree based temporal directed graph. Fractal analysis is performed to find cognitively distinguishable patterns of the malicious processes containing polymorphic malware executables. The main contributions of this paper are;the presentation of a graph theoretic approach for semantic characterization of polymorphism in the operating system's process tree, and the cognitive feature extraction of the polymorphic behavior for detection over a temporal process space.

关键词： Polymorphic malware cognitive machine learning fractal classification cognitive intelligence internet anomaly detection cyber threats host intrusion detection system HIDS multifractal correlation complexity semantic heuristic features

来源：评论

学校读者我要写书评

暂无评论

Modeling Chunking Effects on learning and Performance using the Computational-Unified learning Model (C-ULM): A Multiagent cognitive Process Model 15

Modeling Chunking Effects on Learning and Performance using ...

引用

15th IEEE International Conference on cognitive Informatics and cognitive Computing (ICCI*CC)

作者： Shell, Duane F. Soh, Leen-Kiat Chiriacescu, Vlad Univ Nebraska Dept Educ Psychol Lincoln NE 68588 USA Univ Nebraska Dept Comp Sci & Engn Lincoln NE 68588 USA Simudyne London England

ISBN: (纸本)9781509038466

Chunking has emerged as a basic property of human cognition. Computationally, chunking has been proposed as a process for compressing information also has been identified in neural processes in the brain and used in models of these processes. Our purpose in this paper is to expand understanding of how chunking impacts both learning and performance using the Computational-Unified learning Model (C-ULM) a multi-agent computational model. Chunks in C-ULM long-term memory result from the updating of concept connection weights via statistical learning. Concept connection weight values move toward the accurate weight value needed for a task and a confusion interval reflecting certainty in the weight value is shortened each time a concept is attended in working memory and each time a task is solved, and the confusion interval is lengthened when a chunk is not retrieved over a number of cycles and each time a task solution attempt fails. The dynamic tension between these updating mechanisms allows chunks to come to represent the history of relative frequency of co-occurrence for the concept connections present in the environment;thereby encoding the statistical regularities in the environment in the long-term memory chunk network. In this paper, the computational formulation of chunking in the C-ULM is described, followed by results of simulation studies examining impacts of chunking versus no chunking on agent learning and agent effectiveness. Then, conclusions and implications of the work both for understanding human learning and for applications within cognitive informatics, artificial intelligence, and cognitive computing are discussed.

关键词： Chunking Statistical learning cognitive process models cognitive machine learning Unified learning Model cognitive processes of the brain cognitive Computing Multiagent Systems

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：