IEICE TRANSACTIONS on Information
Connected Associative Memory Neural Network with Dynamical Threshold Function
Summary :
This paper presents a new connected associative memory neural network. In this network, a threshold function which has two dynamical parameters is introduced. After analyzing the dynamical behaviors and giving an upper bound of the memory capacity of the conventional connected associative memory neural network, it is demonstrated that these parameters play an important role in the recalling processes of the connected neural network. An approximate method of evaluationg their optimum values is given. Further, the optimum feedback stopping time of this network is discussed. Therefore, in our network, the recalling processes are ended at the optimum feedback stopping time whether a state energy has been local minimum or not. The simulations on computer show that the dynamical behaviors of our network are greatly improved. Even though the number of learned patterns is so large as the number of neurons, the statistical properties of the dynamical behaviors of our network are that the output series of recalling processes approach to the expected patterns on their initial inputs.
- Publication
- IEICE TRANSACTIONS on Information Vol.E75-D No.1 pp.170-179
- Publication Date
- 1992/01/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Bio-Cybernetics
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Xin-Min HUANG, Yasumitsu MIYAZAKI, "Connected Associative Memory Neural Network with Dynamical Threshold Function" in IEICE TRANSACTIONS on Information,
vol. E75-D, no. 1, pp. 170-179, January 1992, doi: .
Abstract: This paper presents a new connected associative memory neural network. In this network, a threshold function which has two dynamical parameters is introduced. After analyzing the dynamical behaviors and giving an upper bound of the memory capacity of the conventional connected associative memory neural network, it is demonstrated that these parameters play an important role in the recalling processes of the connected neural network. An approximate method of evaluationg their optimum values is given. Further, the optimum feedback stopping time of this network is discussed. Therefore, in our network, the recalling processes are ended at the optimum feedback stopping time whether a state energy has been local minimum or not. The simulations on computer show that the dynamical behaviors of our network are greatly improved. Even though the number of learned patterns is so large as the number of neurons, the statistical properties of the dynamical behaviors of our network are that the output series of recalling processes approach to the expected patterns on their initial inputs.
URL: https://global.ieice.org/en_transactions/information/10.1587/e75-d_1_170/_p
Copy
@ARTICLE{e75-d_1_170,
author={Xin-Min HUANG, Yasumitsu MIYAZAKI, },
journal={IEICE TRANSACTIONS on Information},
title={Connected Associative Memory Neural Network with Dynamical Threshold Function},
year={1992},
volume={E75-D},
number={1},
pages={170-179},
abstract={This paper presents a new connected associative memory neural network. In this network, a threshold function which has two dynamical parameters is introduced. After analyzing the dynamical behaviors and giving an upper bound of the memory capacity of the conventional connected associative memory neural network, it is demonstrated that these parameters play an important role in the recalling processes of the connected neural network. An approximate method of evaluationg their optimum values is given. Further, the optimum feedback stopping time of this network is discussed. Therefore, in our network, the recalling processes are ended at the optimum feedback stopping time whether a state energy has been local minimum or not. The simulations on computer show that the dynamical behaviors of our network are greatly improved. Even though the number of learned patterns is so large as the number of neurons, the statistical properties of the dynamical behaviors of our network are that the output series of recalling processes approach to the expected patterns on their initial inputs.},
keywords={},
doi={},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - Connected Associative Memory Neural Network with Dynamical Threshold Function
T2 - IEICE TRANSACTIONS on Information
SP - 170
EP - 179
AU - Xin-Min HUANG
AU - Yasumitsu MIYAZAKI
PY - 1992
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E75-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 1992
AB - This paper presents a new connected associative memory neural network. In this network, a threshold function which has two dynamical parameters is introduced. After analyzing the dynamical behaviors and giving an upper bound of the memory capacity of the conventional connected associative memory neural network, it is demonstrated that these parameters play an important role in the recalling processes of the connected neural network. An approximate method of evaluationg their optimum values is given. Further, the optimum feedback stopping time of this network is discussed. Therefore, in our network, the recalling processes are ended at the optimum feedback stopping time whether a state energy has been local minimum or not. The simulations on computer show that the dynamical behaviors of our network are greatly improved. Even though the number of learned patterns is so large as the number of neurons, the statistical properties of the dynamical behaviors of our network are that the output series of recalling processes approach to the expected patterns on their initial inputs.
ER -
English
