A quaternary version of the back-propagation algorithm

A quaternary version, of the back-propagation algorithm is proposed for multilayered neural networks whose weights, threshold values, input and output signals are all quaternions. This new algorithm can be used to learn patterns consisted of quaternions in a natural way. An example was used to successfully test the new formulation.

[1]  John Canny,et al.  The complexity of robot motion planning , 1988 .

[2]  C. Norris.  A structure for learning. , 1958, Nursing outlook.

[3]  T. Nitta.  Structure of learning in the complex numbered back-propagation network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[4]  T. Nitta.  An analysis on decision boundaries in the complex back-propagation network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[5]  Akira Watanabe,et al.  A method to interpret 3D motion using neural networks , 1994, Proceedings of 1st International Conference on Image Processing.

[6]  Clark C. Guest,et al.  Modification of backpropagation networks for complex-valued signal processing in frequency domain , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[7]  T. Nitta.  Generalization ability of the three-dimensional back-propagation network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[8]  Akira Watanabe,et al.  A Method to Interpret 3D Motions Using Neural Networks (Special Section on Information Theory and Its Applications) , 1994 .

[9]  Olivier Faugeras,et al.  Three-Dimensional Computer Vision , 1993 .

[10]  Akira Watanabe,et al.  Interpretation of Optical Flow Through Complex Neural Network , 1993, IWANN.

[11]  T. Nitta.  A backpropagation algorithm for neural networks based an 3D vector product , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[12]  D. Rumelhart.  Parallel Distributed Processing Volume 1: Foundations , 1987 .