TY - JOUR
T1 - Statistical Learning in Vision
AU - Fiser, József
AU - Lengyel, Gábor
N1 - Publisher Copyright:
© 2022 Annual Reviews Inc.. All rights reserved.
PY - 2022/9/15
Y1 - 2022/9/15
N2 - Vision and learning have long been considered to be two areas of research linked only distantly. However, recent developments in vision research have changed the conceptual definition of vision from a signal-evaluating process to a goal-oriented interpreting process, and this shift binds learning, together with the resulting internal representations, intimately to vision. In this review, we consider various types of learning (perceptual, statistical, and rule/abstract) associated with vision in the past decades and argue that they represent differently specialized versions of the fundamental learning process, which must be captured in its entirety when applied to complex visual processes. We show why the generalized version of statistical learning can provide the appropriate setup for such a unified treatment of learning in vision, what computational framework best accommodates this kind of statistical learning, and what plausible neural scheme could feasibly implement this framework. Finally, we list the challenges that the field of statistical learning faces in fulfilling the promise of being the right vehicle for advancing our understanding of vision in its entirety.
AB - Vision and learning have long been considered to be two areas of research linked only distantly. However, recent developments in vision research have changed the conceptual definition of vision from a signal-evaluating process to a goal-oriented interpreting process, and this shift binds learning, together with the resulting internal representations, intimately to vision. In this review, we consider various types of learning (perceptual, statistical, and rule/abstract) associated with vision in the past decades and argue that they represent differently specialized versions of the fundamental learning process, which must be captured in its entirety when applied to complex visual processes. We show why the generalized version of statistical learning can provide the appropriate setup for such a unified treatment of learning in vision, what computational framework best accommodates this kind of statistical learning, and what plausible neural scheme could feasibly implement this framework. Finally, we list the challenges that the field of statistical learning faces in fulfilling the promise of being the right vehicle for advancing our understanding of vision in its entirety.
KW - hierarchical Bayesian modeling
KW - perceptual learning
KW - probabilistic computation
KW - rule learning
KW - statistical learning
KW - structure learning
UR - http://www.scopus.com/inward/record.url?scp=85138446743&partnerID=8YFLogxK
U2 - 10.1146/annurev-vision-100720-103343
DO - 10.1146/annurev-vision-100720-103343
M3 - Review Article
C2 - 35727961
AN - SCOPUS:85138446743
SN - 2374-4642
VL - 8
SP - 265
EP - 290
JO - Annual Review of Vision Science
JF - Annual Review of Vision Science
ER -