Learning-possibility of neuron model can recognize depth-rotation in three-dimension space

We propose a neuron model to learn depth-rotation movement in three-dimensional space. The neuron model imitating neuron structure has a system resembling a neuron. We consider a neuron system, and expect to examine whether the system has reasonable function or not. Koch, Poggio and Torre (1982) believed that inhibition signal would shunt excitation signal on the dendrites, and signal functions as input and delay input. Thus, they were sure that function of directional selectivity is arisen by the delay system. Koch´s conception is so important; therefore, we construct our neuron system based on their conception. We initialize the connections and the dendrites by random data, and train them by the back-propagation algorithm for three-dimensional movement. After learning, the neuron model for directional selectivity gets the ability of perceiving depth-rotation. It is similar to the real neuron´s morphology.