BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Visual learning: Babies\, bodies and machines - Professor Linda Sm
 ith\, Department of Psychological and Brain Sciences\, Indiana University 
 Bloomington\, USA
DTSTART:20191122T120000Z
DTEND:20191122T133000Z
UID:TALK128752@talks.cam.ac.uk
CONTACT:Louise White
DESCRIPTION:Abstract:  Learning depends on both the learning mechanism and
  the training material. This talk considers the natural statistics of infa
 nt visual experience.   These natural training sets for human visual objec
 t recognition challenge usual assumptions about how we think about learnin
 g.  These visual experiences are created in real time by infants’ own be
 haviors. They change systematically as infants’ bodies and behavior chan
 ges.   Rather than equal experiences with all kinds of things\, toddlers e
 xperience extremely skewed distributions with many repeated occurrences of
  a very few things. And though highly variable when considered as a whole\
 , individual views of things are experienced in a specific order – with 
 slow\, smooth visual changes moment-to-moment\, and developmentally ordere
 d transitions in scene content. The skewed\, ordered\, biased visual exper
 iences of infants and toddlers are the training data that allow human lear
 ners to develop a way to recognize everything\, both the pervasively prese
 nt entities and the rarely encountered ones. The joint consideration of re
 al-world statistics for learning by researchers of human and machine learn
 ing seems likely to bring advances in both disciplines. \nbrief bio:  Lind
 a B. Smith\, Distinguished Professor at Indiana University Bloomington\, i
 s an internationally recognized leader in cognitive science and cognitive 
 development. Taking a complex systems perspective\, she seeks to understan
 d the interdependencies among perceptual\, motor and cognitive development
 s during the first three years of post-natal life. Using wearable sensors\
 , including head-mounted cameras\, she studies how the young learner’s o
 wn behavior creates learning experiences.  The work has led to novel insig
 hts currently being extended through collaborations to robotics and artifi
 cial intelligence. She received her PhD from the University of Pennsylvani
 a in 1977 and immediately joined the faculty at Indiana University.   She 
 won the David E. Rumelhart Prize for theoretical contributions to cognitiv
 e science and is an elected member of both the National Academy of Science
 s and the American Academy of Arts and Science.\n
LOCATION:Ground Floor Lecture Theatre\, Department of Psychology
END:VEVENT
END:VCALENDAR