A model of heteroassociative memory: deciphering surprising features and locations

Abstract

The identification of surprising or interesting locations in an environment is an important problem in the fields of robotics (localisation, mapping and exploration), ar-chitecture (wayfinding, design), navigation (landmark identification) and computational creativity. Despite this familiarity, existing studies are known to rely ei-ther on human studies (in architecture and navigation) or complex feature intensive methods (in robotics) to evaluate surprise. In this paper, we propose a novel het-eroassociative memory architecture that remembers in-put patterns along with features associated with them. The model mimics human memory by comparing and associating new patterns with existing patterns and fea-tures, and provides an account of surprise experienced. The application of the proposed memory architecture is demonstrated by identifying monotonous and surprising locations present in a Google Sketchup model of an en-vironment. An inter-disciplinary approach combining the proposed memory model and isovists (from archi-tecture) is used to perceive and remember the structure of different locations of the model environment. The experimental results reported describe the behaviour of the proposed surprise identification technique, and illus-trate the universal applicability of the method. Finally, we also describe how the memory model can be modi-fied to mimic forgetfulness.