Title :
On the critical points of the complex-valued neural network
Author_Institution :
Neurosci. Res. Inst., Nat. Inst. of Adv. Ind. Sci. & Technol., Ibaraki, Japan
Abstract :
The properties of the critical points caused by the hierarchical structure of complex-valued neural networks are investigated. If the loss function used is not regular as a complex function, the critical points caused by the hierarchical structure are all saddle points.
Keywords :
learning (artificial intelligence); neural nets; optimisation; complex-valued neural networks; critical points; error function; global minimum; hierarchical structure; learning; loss function; Biological neural networks; Joining processes; Neural networks; Neurons; Neuroscience; Telecommunications;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1202792
