A neural network that learns to integrate oculomotor signals

Neurophysiological studies reveal a neural network in the brain stem that converts a velocity to a position signal to mediate the vestibulo reflex. This integrator is calibrated at birth and then maintained through disease and trauma. Therefore, it is a network that learns. It was modeled by a group of interconnected neurons that received a continuous time function at its input and generated a continuous output. The output was monitored to create an error. The network learned on a trial-and-error, synapse-by-synapse algorithm. The resulting network integrated by forming multiple positive feedback loops. Cell behaviour was distributed and resembled that seen with microelectrodes in the real integrator