Differential Neural Network-Based Nonparametric Identification of Eye Response to Enforced Head Motion

Dynamic motion simulators cannot provide the same stimulation of sensory systems as real motion. Hence, only a subset human senses should be targeted. For providing vestibular stimulus, an automatic bodily function vestibular–ocular reflex (VOR) can objectively measure how accurate simulation is. This requires model ocular response to enforced accelerations, attempt create which is shown in this paper. The proposed corresponds single-layer spiking differential neural network with its activation functions are based on dynamic Izhikevich neuron dynamics. An experiment collect training data corresponding controlled accelerated motions that produce VOR, measured using eye-tracking system. effectiveness identification demonstrated by comparing performance traditional sigmoidal identifier. representations produces more approximation foveal estimation mean square error confirms.