BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Phoenix
BEGIN:STANDARD
DTSTART:19671029T010000
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260430T150112Z
UID:80FB7CF0-99FC-4211-9D61-C4CED2D1697D
DTSTART;TZID=America/Phoenix:20260427T090000
DTEND;TZID=America/Phoenix:20260427T100000
DESCRIPTION:Registration Link: https://asq.webex.com/weblink/register/rf28b
 c2df4626a12b2a8f4ced017302ba\n\nThis introductory webinar reframes AI syst
 ems as engineered systems that must be reliable\, auditable\, and safe in 
 changing environments. It surveys common failure modes of deployed models 
 (data drift\, distribution shift\, miscalibration\, pipeline faults\, and 
 human misuse) and outlines an assurance toolbox: testing beyond accuracy\,
  uncertainty-aware “don’t know” behavior\, monitoring\, versioning\,
  rollback\, and governance. The goal is to help reliability engineers appl
 y familiar reliability thinking (FMEA-like reasoning\, controls\, continuo
 us improvement) to build trustworthy AI in production.\n\nSpeaker: Dr. Ron
 g Pan\n\nAgenda: \n- Introduction &amp; Goals\n- AI as Engineered Systems\n- C
 ommon Failure Modes\n- Reliability Thinking (FMEA mindset)\n- AI Assurance
  Toolbox\n- Key Takeaways\n- Q&amp;A\n\nVirtual: https://events.vtools.ieee.or
 g/m/553982
LOCATION:Virtual: https://events.vtools.ieee.org/m/553982
ORGANIZER:cramiscal@ieee.org
SEQUENCE:16
SUMMARY:ASQ RRD series webinar: Reliability of AI
URL;VALUE=URI:https://events.vtools.ieee.org/m/553982
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;Registration Link: &lt;a href=&quot;https://asq.we
 bex.com/weblink/register/rf28bc2df4626a12b2a8f4ced017302ba&quot;&gt;https://asq.we
 bex.com/weblink/register/rf28bc2df4626a12b2a8f4ced017302ba&lt;/a&gt;&lt;/p&gt;\n&lt;p&gt;Thi
 s introductory webinar reframes AI systems as engineered systems that must
  be reliable\, auditable\, and safe in changing environments. It surveys c
 ommon failure modes of deployed models (data drift\, distribution shift\, 
 miscalibration\, pipeline faults\, and human misuse) and outlines an assur
 ance toolbox: testing beyond accuracy\, uncertainty-aware &amp;ldquo\;don&amp;rsqu
 o\;t know&amp;rdquo\; behavior\, monitoring\, versioning\, rollback\, and gove
 rnance. The goal is to help reliability engineers apply familiar reliabili
 ty thinking (FMEA-like reasoning\, controls\, continuous improvement) to b
 uild trustworthy AI in production.&lt;/p&gt;\n&lt;p&gt;Speaker: Dr. Rong Pan&lt;/p&gt;&lt;br /&gt;
 &lt;br /&gt;Agenda: &lt;br /&gt;&lt;ul&gt;\n&lt;li data-section-id=&quot;1ni1ys8&quot; data-start=&quot;44&quot; da
 ta-end=&quot;68&quot;&gt;Introduction &amp;amp\; Goals&lt;/li&gt;\n&lt;li data-section-id=&quot;3hdcl8&quot; d
 ata-start=&quot;69&quot; data-end=&quot;97&quot;&gt;AI as Engineered Systems&lt;/li&gt;\n&lt;li data-secti
 on-id=&quot;ngrvrp&quot; data-start=&quot;98&quot; data-end=&quot;122&quot;&gt;Common Failure Modes&lt;/li&gt;\n&lt;
 li data-section-id=&quot;1a4fbgq&quot; data-start=&quot;123&quot; data-end=&quot;162&quot;&gt;Reliability T
 hinking (FMEA mindset)&lt;/li&gt;\n&lt;li data-section-id=&quot;30crwi&quot; data-start=&quot;163&quot;
  data-end=&quot;187&quot;&gt;AI Assurance Toolbox&lt;/li&gt;\n&lt;li data-section-id=&quot;12q4fuh&quot; d
 ata-start=&quot;188&quot; data-end=&quot;205&quot;&gt;Key Takeaways&lt;/li&gt;\n&lt;li data-section-id=&quot;1o
 4s4e&quot; data-start=&quot;206&quot; data-end=&quot;211&quot; data-is-last-node=&quot;&quot;&gt;Q&amp;amp\;A&lt;/li&gt;\n
 &lt;/ul&gt;
END:VEVENT
END:VCALENDAR