报 告 人：Witold Pedrycz院士
工作单位：阿尔伯塔大学（加拿大）
报告题目：机器学习架构的可信度：设计自我意识机制
报告时间：2023年5月22日（周一）14:30-15:30
报告链接：Teams Link
https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d
内容摘要：
近年来，我们见证了人工智能和机器学习（ML）的巨大成就和诸多现实应用。高效和系统地设计其架构固然重要，而旨在对所获结果质量进行评价的综合评估机制也同样重要。ML模型的可信度也是所有应用程序的关注点，特别是在自治系统中常见的具有高度临界性的应用程序。在这方面存在亟待解决的问题：如何量化由ML模型产生结果的质量？它的可信度是多少？如何为模型配备一些自我意识机制，以便能够触发对额外的支持性实验依据的关键指导？通过对概念性和算法上的追求，我们认为这些问题可以在粒计算的设置中形式化，即任何数字结果都可以被相关的信息颗粒所增强，并且结果的质量被表示为信息颗粒的特征，如覆盖范围和特异性。这项研究涵盖了不同的方向，包括置信/预测区间、ML模型的颗粒嵌入和颗粒高斯过程模型。本报告将讨论在迁移学习、知识蒸馏和联邦学习领域的几个具有代表性的应用。
个人简介：
Witold Pedrycz院士（IEEE终身会士）是加拿大埃德蒙顿阿尔伯塔大学电气和计算机工程系的教授，也是波兰科学院的外籍院士和加拿大皇家学会的会员，并在波兰华沙的波兰科学院系统研究所任职。Witold Pedrycz院士曾获多个奖项，包括IEEE系统、人类和控制论学会的诺伯特-维纳奖，IEEE加拿大计算机工程奖，欧洲软计算中心的卡贾斯特尔软计算奖，基拉姆奖，IEEE计算智能学会的模糊先锋奖，以及2019年IEEE系统、人类和控制论学会的功勋服务奖。Witold Pedrycz院士的主要研究领域涉及计算智能、颗粒计算和机器学习等。Witold Pedrycz院士现任《Information Sciences》主编、《WIREs Data Mining and Knowledge Discovery (Wiley)》主编及《Int. J. of Granular Computing(Springer)》和《J. of Data Information and Management (Springer)》的联合主编。
【编辑：王健】
英文版：
Academic Report Notice of Witold Pedrycz : Credibility of Machine Learning Architectures: Designing Self-Awareness Mechanisms
Speaker: Academician Witold Pedrycz
Title: Credibility of Machine Learning Architectures: Designing Self-Awareness Mechanisms
Time: 14:30 pm, May 22, 2023 (Monday)
Link: https://teams.microsoft.com/l/meetup-join/19%3aB4gmRcUATAMA2iJqi-xXvtfPFfTbxVJPxSW_pcAPBao1%40thread.tacv2/1638719716825?context=%7b%22Tid%22%3a%2222804ebb-30d5-47df-942f-f3a3722f0225%22%2c%22Oid%22%3a%2216a60c03-ad7a-4b85-a403-8ebd947e010c%22%7d
Abstract:
Over the recent years, we have been witnessing spectacular and far-reaching achievements and applications of Artificial Intelligence and Machine Learning (ML), in particular. Efficient and systematic design of their architectures is important. Equally important are comprehensive evaluation mechanisms aimed at the assessment of the quality of the obtained results. The credibility of ML models is also of concern to any application, especially the one exhibiting a high level of criticality commonly encountered in autonomous systems. With this regard, there are a number of burning questions: how to quantify the quality of a result produced by the ML model? What is its credibility? How to equip the models with some self-awareness mechanism so careful guidance for additional supportive experimental evidence could be triggered? Proceeding with a conceptual and algorithmic pursuits, we advocate that these problems could be formalized in the settings of Granular Computing. We show that any numeric result be augmented by the associated information granules and the quality of the results is expressed in terms of the characteristics of information granules such as coverage and specificity. Different directions are covered including confidence/ prediction intervals, granular embedding of ML models, and granular Gaussian Process models. Several representative and direct applications in the realm of transfer learning, knowledge distillation, and federated learning are discussed.
Personal Introduction:
Witold Pedrycz (IEEE Life Fellow) is Professor in the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada. He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland. Dr. Pedrycz is a foreign member of the Polish Academy of Sciences and a Fellow of the Royal Society of Canada. He is a recipient of several awards including Norbert Wiener award from the IEEE Systems, Man, and Cybernetics Society, IEEE Canada Computer Engineering Medal, a Cajastur Prize for Soft Computing from the European Centre for Soft Computing, a Killam Prize, a Fuzzy Pioneer Award from the IEEE Computational Intelligence Society, and 2019 Meritorious Service Award from the IEEE Systems Man and Cybernetics Society. His main research directions involve Computational Intelligence, Granular Computing, and Machine Learning, among others. Professor Pedrycz serves as an Editor-in-Chief of Information Sciences, Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley), and Co-editor-in-Chief of Int. J. of Granular Computing (Springer) and J. of Data Information and Management (Springer).
[Editor: Jian Wang]