Mental Rotation by Neural Network

In this paper, we propose a neural network with a mental rotation function composed of two, rotation and comparison functions, and discuss its feasibility. The proposed network will output its result of judgment concerning their coincidence or non-coincidence, when two figures are input. If they coincide, the network will output the angle of difference between the two figures. The training for learning the mental rotation is made by teaching the network all rotated figures at every 22.5 degrees. Consequently, realization of the target network was confirmed by simulation experiments.