Three-Dimensional Vector Valued Neural Network and its Generalization Ability

作者: Tohru Nitta , Aist Tsukuba Central

DOI:

关键词:

摘要: This letter introduces a novel neural network whose input and output signals, threshold values are all 3-dimensional real-valued vectors weights orthogonal matrices, the related back-propagation learning algorithm. The algorithm allows new spatial characteristics to be treated.

参考文章(4)
Akira Hirose, None, Complex-Valued Neural Networks: Theories and Applications WORLD SCIENTIFIC. ,(2003) , 10.1142/5345
Arata Miyauchi, Minami Miyauchi, Nobuyuki Yazawa, Akira Watanabe, A method to interpret 3D motions using neural networks IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences. ,vol. 77, pp. 1363- 1370 ,(1994)
RGM Morris, Parallel & distributed processing ACM SIGGRAPH 2005 Courses on - SIGGRAPH '05. pp. 11- ,(2005) , 10.1145/1198555.1198750
Tohru Nitta, An extension of the back-propagation algorithm to complex numbers Neural Networks. ,vol. 10, pp. 1391- 1415 ,(1997) , 10.1016/S0893-6080(97)00036-1