English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Hierarchically structured representations facilitate visual understanding

Schwartenbeck, P., Éltetö, N., Braun, A., Bányai, M., & Dayan, P. (2022). Hierarchically structured representations facilitate visual understanding. Poster presented at 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022), Providence, RI, USA.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Schwartenbeck, P1, Author              
Éltetö, N1, Author              
Braun, A1, Author              
Bányai, M1, Author              
Dayan, P1, Author              
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              

Content

show
hide
Free keywords: -
 Abstract: Biological agents are adept at flexibly solving a wide range of cognitively challenging decision-making problems given woefully little experience. This capacity rests on one fact about the problems themselves: that there is substantial recurring structure; and two facts about us: that we can extract the structure and build internal representations of it based on the statistics of observations, and that we can use those representations when solving new tasks. Artificial agents could benefit from copying these characteristics. An important form of statistical structure is a hierarchy. We therefore investigated the formation of hierarchical representations in human subjects using a novel, sophisticated, shape composition task, in which subjects learn how composite shapes are formed from a restricted set of basic building blocks. Understanding a new shape in these terms has been shown to involve a form of internal, imagined, construction process. The task involved hierarchical structure with certain pairs of building blocks tending to co-occur as hierarchical ’chunks’. Picking up on these chunks would facilitate the task of understanding new shapes. We found that subjects learnt and employed hierarchically structured representations when composing visual shapes. Further, we found that subjects generalised these structured representations to unseen stimuli. Subjects correctly identified previously unseen shapes that contained hierarchical structure to be more likely to be part of the training set compared to random shapes with no hierarchical structure. Further, when asked to complete novel shapes, subjects relied on hierarchical structure to generate solutions. Taken together, this suggests humans possess strong inductive biases for learning, employing, and generalising hierarchical structures in visual understanding. The computational and neural bases of these capacities are not yet clear.

Details

show
hide
Language(s):
 Dates: 2022-05
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022)
Place of Event: Providence, RI, USA
Start-/End Date: 2022-06-08 - 2022-06-11

Legal Case

show

Project information

show

Source 1

show
hide
Title: 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 1.23 Start / End Page: 23 - 24 Identifier: -