A neural network model of curiosity-driven infant categorization

Katherine E. Twomey, Gert Westermann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Infants are curious learners who drive their own cognitive development by imposing structure on their learning environments as they explore. Understanding the mechanisms underlying this curiosity is therefore critical to our understanding of development. However, very few studies have examined the role of curiosity in infants' learning, and in particular, their categorization; what structure infants impose on their own environment and how this affects learning is therefore unclear. The results of studies in which the learning environment is structured a priori are contradictory: while some suggest that complexity optimizes learning, others suggest that minimal complexity is optimal, and still others report a Goldilocks effect by which intermediate difficulty is best. We used an auto-encoder network to capture empirical data in which 10-month-old infants' categorization was supported by maximal complexity [1]. When we allowed the same model to choose stimulus sequences based on a "curiosity" metric which took into account the model's internal states as well as stimulus features, categorization was better than selection based solely on stimulus characteristics. The sequences of stimuli chosen by the model in the curiosity condition showed a Goldilocks effect with intermediate complexity. This study provides the first computational investigation of curiosity-based categorization, and points to the importance characterizing development as emerging from the relationship between the learner and its environment.

Original languageEnglish
Title of host publication5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015
PublisherIEEE
Pages1-6
Number of pages6
ISBN (Electronic)9781467393201
DOIs
Publication statusPublished - 2 Dec 2015
Event5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015 - Providence, United States
Duration: 13 Aug 201516 Aug 2015

Conference

Conference5th Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2015
Country/TerritoryUnited States
CityProvidence
Period13/08/1516/08/15

Keywords

  • Curiosity
  • Infant Categorization
  • Intrinsic Motivation
  • Neural Network
  • Variability

Fingerprint

Dive into the research topics of 'A neural network model of curiosity-driven infant categorization'. Together they form a unique fingerprint.

Cite this