BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:270@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20250521T163000
DTEND;TZID=America/Los_Angeles:20250521T172000
DTSTAMP:20250505T225555Z
URL:https://escience.washington.edu/events/uw-data-science-seminar-boris-k
 ovalerchuk/
SUMMARY:UW Data Science Seminar: Boris Kovalerchuk
DESCRIPTION:Please join us for a UW Data Science Seminar featuring Boris Ko
 valerchuk from the Department of Computer Science at Central Washington Un
 iversity on  Wednesday\, May 21st from 4:30 to 5:20 p.m. PT. The seminar w
 ill be held in Electrical and Computer Engineering Building 125 – Campu
 s Map.\n"How to Identify and Avoid Quasi-Explanation in AI and Machine Lea
 rning"\n\nAbstract:  Low-quality explanations of predictive models prevent
  domain experts from trusting and deploying models in high-stakes domains 
 like medicine\, even when these black-box models are accurate. Explanation
 s suitable for data scientists to debug models and improve accuracy differ
  from those required for domain experts to confidently risk deploying mode
 ls in critical applications. Unfortunately\, popular explanation methods o
 ften generate quasi-explanations that fail to meet domain experts’ needs
 . Crucially\, these methods bring foreign assumptions to the domain on top
  of those already brought by black-box models\, most of which remain hidde
 n and are difficult for domain experts to assess. To address this\, we adv
 ocate for explicitly revealing these assumptions\, enabling domain experts
  to critically assess their validity. We will present methods that produce
  explanations free from such foreign assumptions\, supported by open-sourc
 e software. These include interactive Visual Knowledge Discovery (VKD) met
 hods\, grounded in a novel framework for lossless visualization of multidi
 mensional data by General Line Coordinates (GLC). It complements other AI/
 ML techniques\, bridging the gap between technical accuracy and domain-spe
 cific interpretability.\n\n  Biography:  Dr. Boris Kovalerchuk is a profes
 sor of Computer Science at Central Washington University. His publication 
 activities include five books published by Springer:"Data Mining in Financ
 e (2000)\, "Visual and Spatial Analysis" (2005)\, "Visual Knowledge Discov
 ery and Machine Learning" (2018)\, “Integrating Artificial Intelligence 
 and Visualization for Visual Knowledge Discovery” (2022)\, and “Artifi
 cial Intelligence and Visualization: Advancing Visual Knowledge Discovery
 ” (2024)\, chapters in the Data Mining/Machine Learning Handbooks (2006\
 , 2010\, 2023) with total over 200 publications. He coined the terms Visua
 l Knowledge Discovery (VKD) and General Line Coordinates (GLC)\, which lin
 k AI and visualization frontiers. Dr. Kovalerchuk has been a principal inv
 estigator of research projects supported by the US Government agencies and
  a senior visiting scholar at the Air Force Research Lab. He delivered rel
 evant tutorials at major conferences.\n\nThe 2024-2025 seminars will be he
 ld in person\, and are free and open to the public.
ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa
 ds/2025/05/BorisSeminar.jpg
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR