Title :
The variable neighborhood CNN
Author :
Namba, M. ; Takatori, S. ; Kawabata, H. ; Zhang, Z.
Author_Institution :
Fac. of Comput. Sci. & Syst. Eng., Okayama Prefectural Univ., Japan
Abstract :
The cellular neural network (CNN) has been widely used for associative memory. However, it has a problem called indeterminate cell. We describe this problem and propose the variable neighborhood CNN. As a result, we have been able to avoid the problem, and construct a more efficient CNN system for associative memory in simulation
Keywords :
cellular neural nets; content-addressable storage; singular value decomposition; SVD; algorithm searching; associative memory; computation time; indeterminate cell problem; memory patterns; stable equilibrium points; variable neighborhood CNN; Analog circuits; Cellular neural networks; Circuit noise; Computer science; Equations; Feature extraction; Liver diseases; Systems engineering and theory;
Conference_Titel :
Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6685-9
DOI :
10.1109/ISCAS.2001.921257
