Title :
A study of neural network based on quaternion
Author :
Kusakabe, T. ; Isokawa, T. ; Kouda, Noriaki ; Matsui, Nobuyuki
Author_Institution :
Graduate Sch. of Eng., Himeji Inst. of Technol., Hyogo, Japan
Abstract :
A quaternion neural network with nonlinear function is presented in this paper. The quaternion neuron adopts geometrical transformations as operators of data to be processed. Back Propagation for the layered network: with quaternion neurons is also formulated. The simulation results show that the presented model has the ability in learning affine transformation of 3D figures. while conventional neural network can hardly acquire.
Keywords :
learning (artificial intelligence); neural nets; nonlinear functions; atfine transformation; geometrical transformations; learning; learning atfine transformation; nonlinear function; quaternion neural network; quaternion neuron; Computational modeling; Indium phosphide; Intrusion detection; Lungs; Neural networks; Neurons; Quaternions; Robots;
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
DOI :
10.1109/SICE.2002.1195247
