Familiarity-to-novelty shift driven by learning: A conceptual and computational model

摘要

We propose a new theory explaining the familiarity-to-novelty shift in infant habituation. In our account, infants' interest in a stimulus is related to their learning progress, i.e. the improvement of an internal model of the stimulus. Specifically, we propose infants prefer the stimulus for which its current learning progress is maximal. We also propose a new algorithm called Selective Learning Self Organizing Map (SL-SOM), a biologically inspired modification to SOM, exhibiting familiarity-to-novelty shift. Using this algorithm we present experiments on a robotic platform.