BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Neural Circuits & Behavior Progress Report // Oh Hyeon Choung - Re
 current Networks but not Classic CNNs Explain Global Shape Processing
DTSTART:20191107T093000
DTEND:20191107T103000
DTSTAMP:20260406T194722Z
UID:d0ca22b665cd65a828844959ddd4c803d4328372b4480f1f677c07cc
CATEGORIES:Conferences - Seminars
DESCRIPTION:Oh Hyeon Choung\, Prof. Herzog's Lab\nFeedforward Convolutiona
 l Neural Networks (ffCNNs) have become state-of-the-art models in computer
  vision and neuroscience. However\, ffCNNs only roughly mimic human vision
 . They lack recurrent connections and rely mainly on local features\, cont
 rary to humans who use global shape computations. Here\, using visual crow
 ding as a well-controlled and specific probe for global shape computations
 \, we show that ffCNNs cannot produce human-like processing for principled
  architectural reasons. We provide evidence that recurrent processing is c
 rucial for global shape computations in both humans and machines. In parti
 cular\, we show that Capsule Networks\, combining ffCNNs with a time-consu
 ming recurrent grouping and segmentation mechanism\, can solve this challe
 nge in a natural manner. Together\, we suggest recurrent grouping and segm
 entation processes are essential to understand the human visual system and
  create better models that harness global shape computations.\n 
LOCATION:SV 1717 https://plan.epfl.ch/?room==SV%201717
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR