报告题目：From Design to Deployment of Machine Learning Technology: An Environment of Granular Computing 

报告所属学科：管理科学与工程

报告人：Witold Pedrycz（加拿大阿尔伯塔大学）

报告时间：2023年11月8日、11月22日、11月29日、12月6日 周三10:00-11:30

报告地点：腾讯会议：388-8518-7764 QQ群：687807963

报告摘要：

(1) Introductory comments

The key agenda of Machine Learning. Main concepts. Deployment of Machine Learning and fundamental quests. Challenges of Machine Learning: credibility (confidence), interpretability and explainability, privacy.

(2) Granular Computing: a primer

Concepts, motivation, examples. Design of information granules, rule-based architectures: symbolic- subsymbolic perspective. Learning schemes.

(3) Credibility of ML architectures and their results

Motivation. Granular embedding and Gaussian Process augmentation. Mechanisms of active learning. 

(4) Interpretability and explainability

Processes of interpretability and explainability. Inductive and deductive reasoning. Counterfactual reasoning.  Local linear models. Shapley value.

(5) Privacy in ML: a case of federated learning

Motivating factors behind federated learning: coping with data islands, average and gradient federated learning, Federated learning-based rule design, granular assessment and performance analysis.

报告人简介：

Witold Pedrycz，加拿大阿尔伯塔大学讲席教授，加拿大皇家科学院院士，波兰科学院外籍院士，电气和电子工程师协会会士。现担任《Information Sciences》和《Wiley Interdisciplinary Review Data Mining and Knowledge Discovery》主编，及《Granular Computing》共同主编。主要研究方向包括粒计算、智能系统、模糊集和模糊系统、模式识别等；并发表多篇高质量论文，出版著作21本，H指数123，计算机科学和电子学排名第71位。