{"id":2701,"date":"2026-07-17T20:14:50","date_gmt":"2026-07-17T12:14:50","guid":{"rendered":"https:\/\/ele.mcu.edu.tw\/icsse2026\/?page_id=2701"},"modified":"2026-07-17T20:42:04","modified_gmt":"2026-07-17T12:42:04","slug":"keynote1","status":"publish","type":"page","link":"https:\/\/ele.mcu.edu.tw\/icsse2026\/keynote1\/","title":{"rendered":"Keynote Speech – I"},"content":{"rendered":"\n
\n
\n
\"\"<\/figure><\/div>\n<\/div>\n\n\n\n
\n

Towards Explainable AI Using Deep Fuzzy Neural Networks for Image Classification and Regression<\/strong><\/p>\n\n\n\n

\n\n\n\n

Prof. Chia-Feng Juang<\/strong><\/p>\n\n\n\n

Chair Professor, IEEE Fellow
Department of Electrical Engineering
National Chung Hsing University, Taiwan<\/p>\n<\/div>\n<\/div>\n\n\n\n

Abstract<\/strong> <\/p>\n\n\n\n

AI has emerged as a popular research topic in recent years, demonstrating significant success across various applications. However, most AI models operate as black boxes, making it difficult to explain the reasoning behind their decisions. In response to this challenge, explainable AI (XAI) has garnered substantial attention from researchers. Approaches to achieving XAI generally fall into two categories: intrinsic model interpretability and post-hoc explanations. In this speech, I will introduce a series of visually interpretable fuzzy neural networks (VIFNNs) that we have developed. The VIFNNs employ fuzzy if\u2013then rules to process deep convolutional feature maps extracted from images. All the rules are learned through both structural and parameter learning. To enable visual interpretation of these learned fuzzy rules, I will present a technique that employs a deep decoder to map the antecedent of a fuzzy rule to an image. I will also discuss how Gradient-weighted Class Activation Mapping (Grad-CAM), a widely used method, is used for post-hoc explanations of image classification results within the VIFNN. The applications of VIFNNs to human-posture classification, glomerular morphology classification in medical images, and image-based robot localization will be presented.<\/p>\n\n\n\n

Biography:<\/strong><\/p>\n\n\n\n

Chia-Feng Juang received the B.S. and Ph.D. degrees in Control Engineering from the National Chiao-Tung University, Hsinchu, Taiwan, in 1993 and 1997, respectively. Since 2001, he has been with the Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan, where he was appointed Distinguished Professor in 2009 and has served as Chair Professor since 2025. He served as the Chapter Chair of IEEE Computational Intelligence, Taipei Chapter, in 2017-2018. He has served as the President of Taiwan Fuzzy Systems Associations (TFSA) since 2026. Dr. Juang has authored or coauthored over 120 journal papers (including over 65 IEEE journal papers), four books, ten book chapters, and over 150 conference papers. His current research interests include computational intelligence, intelligent control, computer vision, intelligent robots, and AI-aided medical diagnosis.
Dr. Juang was the receipt of the Outstanding Electrical Engineering Professor Award from Chinese Institute of Electrical Engineering, Taiwan, in 2019; the Outstanding Research Award from Ministry of Science and Technology, Taiwan, in 2021; and the Outstanding Research Award from National Science and Technology Council, Taiwan, in 2026. He was elevated to IEEE Fellow in 2019 and International Fuzzy Systems Association (IFSA) Fellow in 2023. He was an IEEE Computational Intelligence Society Distinguished Lecture during 2020-2023. He is currently an Associate Editor for IEEE Transactions on Fuzzy Systems and Asian Journal of Control and an Area Editor for International Journal of Fuzzy Systems.<\/p>\n\n\n\n

\n","protected":false},"excerpt":{"rendered":"

Towards Explainable AI Using Deep Fuzzy Neural Networks for … <\/p>\n

Read More<\/a><\/div>\n","protected":false},"author":209,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"template-blank-1.php","meta":{"_themeisle_gutenberg_block_has_review":false,"_vp_format_video_url":"","_vp_image_focal_point":[]},"acf":[],"_links":{"self":[{"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/pages\/2701"}],"collection":[{"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/users\/209"}],"replies":[{"embeddable":true,"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/comments?post=2701"}],"version-history":[{"count":2,"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/pages\/2701\/revisions"}],"predecessor-version":[{"id":2719,"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/pages\/2701\/revisions\/2719"}],"wp:attachment":[{"href":"https:\/\/ele.mcu.edu.tw\/icsse2026\/wp-json\/wp\/v2\/media?parent=2701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}