In this paper, a middle-mapping learning algorithm for cellular associative memories is presented. This algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the ourter product method. It can guarantee each prototype is stored at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Chen HE, Akio USHIDA, "Iterative Middle Mapping Learning Algorithm for Cellular Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E77-A, no. 4, pp. 706-715, April 1994, doi: .
Abstract: In this paper, a middle-mapping learning algorithm for cellular associative memories is presented. This algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the ourter product method. It can guarantee each prototype is stored at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e77-a_4_706/_p
Copy
@ARTICLE{e77-a_4_706,
author={Chen HE, Akio USHIDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Iterative Middle Mapping Learning Algorithm for Cellular Neural Networks},
year={1994},
volume={E77-A},
number={4},
pages={706-715},
abstract={In this paper, a middle-mapping learning algorithm for cellular associative memories is presented. This algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the ourter product method. It can guarantee each prototype is stored at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Iterative Middle Mapping Learning Algorithm for Cellular Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 706
EP - 715
AU - Chen HE
AU - Akio USHIDA
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E77-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 1994
AB - In this paper, a middle-mapping learning algorithm for cellular associative memories is presented. This algorithm makes full use of the properties of the cellular neural network so that the associative memory has some advantages compared with the memory designed by the ourter product method. It can guarantee each prototype is stored at an equilibrium point. In the practical implementation, it is easy to build up the circuit because the weight matrix presenting the connection between cells is not symmetric. The synchronous updating rule makes its associative speed very fast compared to the Hopfield associative memory.
ER -