BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251113T023110Z
UID:697081D7-95C0-4218-B0D0-2CCBB81FFA25
DTSTART;TZID=America/Los_Angeles:20251024T140000
DTEND;TZID=America/Los_Angeles:20251024T160000
DESCRIPTION:Neural networks have become the foundation of modern artificial
  intelligence\, driving breakthroughs in computer vision\, natural languag
 e processing\, and countless real-world applications. Yet despite their su
 ccess\, today’s models still exhibit surprising limitations: they genera
 lize poorly outside their training distribution\, struggle with reasoning 
 and abstraction\, and often behave as opaque “black boxes.” This semin
 ar takes a deeper look into what neural networks truly do well—and what 
 is still fundamentally missing. We will explore the gaps between pattern r
 ecognition and genuine understanding\, discuss challenges such as interpre
 tability\, robustness\, data efficiency\, and alignment with human intent\
 , and highlight emerging ideas that aim to move beyond current architectur
 es. The goal is to give students a clearer\, more critical perspective on 
 neural networks: not just how they work\, but what remains unsolved\, and 
 where the next opportunities for innovation lie.\n\nSpeaker(s): \, Fan Jia
 ng\n\nBig Data and Artificial Intelligence Research Laboratory\, Universit
 y of Northern British Columbia\, Prince George\, British Columbia\, Canada
LOCATION:Big Data and Artificial Intelligence Research Laboratory\, Univers
 ity of Northern British Columbia\, Prince George\, British Columbia\, Cana
 da
ORGANIZER:Fan.Jiang@unbc.ca
SEQUENCE:8
SUMMARY:A Deeper Look into Neural Networks – What is Missing?
URL;VALUE=URI:https://events.vtools.ieee.org/m/514253
X-ALT-DESC:Description: <br /><p>Neural networks have become the foundation
  of modern artificial intelligence\, driving breakthroughs in computer vis
 ion\, natural language processing\, and countless real-world applications.
  Yet despite their success\, today&rsquo\;s models still exhibit surprisin
 g limitations: they generalize poorly outside their training distribution\
 , struggle with reasoning and abstraction\, and often behave as opaque &ld
 quo\;black boxes.&rdquo\; This seminar takes a deeper look into what neura
 l networks truly do well&mdash\;and what is still fundamentally missing. W
 e will explore the gaps between pattern recognition and genuine understand
 ing\, discuss challenges such as interpretability\, robustness\, data effi
 ciency\, and alignment with human intent\, and highlight emerging ideas th
 at aim to move beyond current architectures. The goal is to give students 
 a clearer\, more critical perspective on neural networks: not just how the
 y work\, but what remains unsolved\, and where the next opportunities for 
 innovation lie.</p>
END:VEVENT
END:VCALENDAR