An Auto-Correlation Associative Memory which Has an Energy Function of Higher Order
スポンサーリンク
概要
- 論文の詳細を見る
A noise tolerant auto-correlation associative memory is proposed. An associated energy function is formed by a multiplication of plural Hopfield's energy functions each of which includes single pattern as its energy minimum. An asynchronous optimizing algorithm of the whole energy function is also presented based on the binary neuron model. The advantages of this new associative memory are that the orthogonality relation among patterns does not need to be satisfied and each stored pattern has a large basin of attraction around itself. The computer simulations show a fairly good performance of associative memory for arbitrary pattern vectors which are not orthogonal to each other.
- 社団法人電子情報通信学会の論文
- 1995-03-25
著者
-
MIYAJIMA Hiromi
Faculty of Engineering, Kagoshima University
-
Murashima S
Kagoshima Univ. Kagoshima‐shi Jpn
-
MURASHIMA Sadayuki
Faculty of Engineering, Kagoshima University
-
Fuchida Takayasu
Faculty of Engineering, Kagoshima University
-
Ida Toshihiro
Faculty of Engineering, Kagoshima University
-
Toyohira Takayuki
Faculty of Engineering, Kagoshima University
-
Fuchida T
Kagoshima Univ. Kagoshima‐shi Jpn
-
Miyajima Hiromi
Faculty Of Engineering Kagoshima University
-
Ida Toshihiro
Faculty Of Engineering Kagoshima University
-
Toyohira Takayuki
Faculty Of Engineering Kagoshima University
関連論文
- A Creating Method of Fuzzy Inference Rules by Self-Creating Neural Network
- Constructive, Destructive and Simplified Learning Methods of Fuzzy Inference
- Maximum Finding on One-Way Mesh-Connected Computers with Multiple Buses (Special Section of Papers Selected from ITC-CSCC'96)
- On Efficient Spare Arrangements and an Algorithm with Relocating Spares for Reconfiguring Processor Arrays (Special Section of Papers Selected from ITC-CSCC'96)
- On Methods for Reconfiguring Processor Arrays (Special Issue on Architectures, Algorithms and Networks for Massively parallel Computing)
- On Some Dynamical Properties of Threshold and Homogeneous Networks (Special Section on Nonlinear Theory and Its Applications)
- An Auto-Correlation Associative Memory which Has an Energy Function of Higher Order
- Competitive Learning Methods with Refractory and Creative Approaches (Special Section on Nonlinear Theory and Its Applications)
- Fuzzy Modeling in Some Reduction Methods of Inference Rules(Nonlinear Problems)(Regular Section)
- Construction Method of Fuzzy Inference by Rule Creation(Special Section on Papers Selected from ITC-CSCC 2002)
- State Sharing Methods in Statistical Fluctuation for Image Restoration(Nonlinear Theory and its Applications)