管理员登录 / English
From Data to Concepts: Augmented Principles, Symbolic-Granular Descriptions, and Quality Analysis
发布时间: 2018-07-09     11:05   【返回上一页】 发布人:Witold Pedrycz


北京师范大学数学科学学院

 

周五公众报告

 

报告题目:From Data to Concepts: Augmented Principles, Symbolic-Granular Descriptions, and Quality Analysis

 

报告人:Witold Pedrycz (阿尔伯塔大学)

 

时间地点:2018年7月27日15:00-16:00,后主楼1124

 

邀请人:于福生

 

报告摘要:Concepts constitute a concise manifestation of key features of data. As being built at the higher level of abstraction than the data themselves, they capture the essence of the data and usually emerge in the form of information granules. 

    We identify three main ways in which an concepts are encountered and characterized: (i) numeric, (ii) symbolic, and (iii) granular. Each of these views come with their advantages and become complementary to some extent. 

   We develop a linkage analysis of concepts built for numerous collections of data (which is a commonly encountered scenario in case of distributed data). Here a framework of a so-called double clustering (viz. a two-phase clustering process) is engaged and a resulting collection of hyper-concepts comes by forming a collection of communities in a graph of concepts.

    We elaborate on the general scheme of processing of granular modeling dwelling upon a collection of granular concepts and yielding a collection of granular models.

 

报告人简介:Witold Pedrycz博士是加拿大阿尔伯塔大学电子与计算机工程系教授,计算机智能研究中心主席,该领域国际著名科学家;2009年当选波兰科学院外籍院士,2012年当选加拿大皇家科学院院士;主要研究方向涉及计算智能、粒度计算、模糊控制、软件工程等诸多领域,在上述领域发表了大量学术论文,完成专著15本;Information Sciences和IEEE Transactions on Systems, Man, and Cybernetics – Systems等杂志主编,IEEE Transactions on Fuzzy Systems、IEEE Transactions on Neural Network等国际杂志编委;2007年,获得IEEE Norbert Wiener Award,2009年,获得Soft Computing领域国际最高奖Cajastur Prize。

 

 

周五学院公众报告主旨:讲解现代数学中的基本概念、重要结果及其数学思想的起源、方法的创新等,扩展我们的年青教师和研究生的视野、提高数学修养以及增强学院的学术氛围。邀请各方向的专家用通俗易懂的报告内容、自由互动的讲解方式展现现代数学中重要的基本概念和深刻原理,让听众可以领略到现代数学理论其实是来源于一些大学或研究生阶段就熟知的古典数学中的想法和结论。希望这些报告有助于高年级的本科生、研究生和年青教师更全面的认识现代数学、享受数学之美。欢迎大家踊跃参与!