Hebbian motor control in a robot-embedded model of habituation

Two experiments using a mobile robot examine the performance of a neural network model of habituation. The input to the network is the video feed from the robot´s camera, preprocessed to model the visual system. Images, after retinal processing, are translated in the frequency domain and Gabor-filtered. The output of the network controls the robot´s motors and thus where it looks. In one condition, network output directly controls the motors. In a second condition, network outputs are connected to control units via weights that are modified with simple Hebbian learning. In both cases, the robot´s behavior reproduces the important familiarity-to-novelty shift observed in human infants. Hebbian learning, however, helps to increase and stabilize novelty preference.