Title :
Beyond object constancy
Author_Institution :
Cognitive Sci. Centre, Southampton Univ., UK
Abstract :
The author amplifies a point made by Pfeifer (1998) about the “fundamental problem of learning category distinctions”. Object constancy (the capacity to see an object as being of constant size and shape despite variation in retinal position and distance from the observer) is certainly one of the most fundamental category invariants that the brain is capable of detecting. The author shows how the principle of detecting and extracting invariants under sensorimotor transformations during sensorimotor interactions with objects can be generalised to more abstract invariants, extracted under more abstract transformations
Keywords :
visual perception; abstract invariants; category distinction learning; invariant detection; invariant extraction; object constancy; retinal distance; retinal position; sensorimotor interactions; sensorimotor transformations;
Conference_Titel :
Self-Learning Robots II: Bio-robotics (Digest No. 1998/248), IEE
Conference_Location :
London
DOI :
10.1049/ic:19980267