A neural network model of curiosity-driven infant categorization

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.