抵抗ヒューズを用いたSOM回路について
スポンサーリンク
概要
- 論文の詳細を見る
In the paper, we propose a novel SOM algorithm that includes resistive fuse characteristic in order to suppress update of synaptic weights by obstructive inputs. Applying the algorithm to some clustering problems, we have confirmed that the novel algorithm exhibits much better performance than conventional one. We also propose an analog implementation example of the novel SOM and the efficient performance is demonstrated.
- 社団法人電子情報通信学会の論文
- 1998-02-05
著者
-
KATAYAMA Kousuke
Graduate School of Engineering, Hiroshima University
-
Saito Toshimichi
Department Of Electrical And Electronic Engineering Hosei University
-
Katayama Kousuke
Department Of Electrical And Electronic Engineering Hosei University
-
Katayama K
Hiroshima Univ. Higashi‐hiroshima‐shi Jpn
-
Saito T
The Department Of Electronics Electrical And Computer Engineering Hosei University
-
Kawahara Shingo
Department of Electrical and Electronic Engineering, HOSEI University
-
Kawahara S
Department Of Electrical And Electronic Engineering Hosei University
-
Saito Toshimichi
Department Of Electrical And Electronic Engineering Faculty Of Engineering Hosei University
関連論文
- An Hadamard Transform Chip Using the PWM Circuit Technique and Its Application to Image Processing(Special Issue on High-Performance Analog Integrated Circuits)
- A High-Resolution Hadamard Transform Circuit Using Pulse Width Modulation Technique
- Basic Dynamics from an Integrate-and-Fire Chaotic Circuit with a Periodic Input
- A GA-Based Learning Algorithm for Binary Neural Networks(Regular Section)
- 抵抗ヒューズを用いたSOM回路について
- 抵抗ヒューズを用いたSOM回路について
- Rich Superstable Phenomena in a Piecewise Constant Nonautonomous Circuit with Impulsive Switching(Oscillation, Dynamics and Chaos,Nonlinear Theory and its Applications)
- Superstable Synchronous Phenomena of Switch-Coupled Relaxation Oscillators
- Return Map Quantization from an Integrate-and-Fire Model with Two Periodic Inputs
- Self-Organization by Chaotic Input
- Manifold Piecewise Constant Systems and Chaos