Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform (Special Section on Selected Papers from the 11th Workshop on Circuits and Systems in Karuizawa)
スポンサーリンク
概要
- 論文の詳細を見る
The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns, which the conventional DTSINN fails to do.
- 社団法人電子情報通信学会の論文
- 1999-03-25
著者
-
Asai Hideki
Faculty Of Engineering Shizuoka University
-
Kamio Takeshi
Faculty Of Engineering Shizuoka University
関連論文
- Relaxation-Based Algorithms for Bipolar Circuit Analysis (Special Section of Papers Selected from JTC-CSCC'93)
- A Fast Algorithm for Spatiotemporal Pattern Analysis of Neural Networks with Multivalued Logic (Special Section on Nonlinear Theory and Its Applications)
- Neural Networks for Digital Sequential Circuits
- Mixed Mode Circuit Simulation Using Dynamic Network Separation and Selective Trace (Special Section on the 6th Karuizawa Workshop on Circuits and Systems)
- Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks(Special Section on Papers Selected from ITC-CSCC 2001)
- Backpropagation Algorithm for LOGic Oriented Neural Nteworks with Quantized Weights and Multilevel Threshold Neurons(Special Section of Selected Papers from the 13th Workshop on Circuits and Systems in Karuizawa)
- Efficient Simulation of Lossy Coupled Transmission Lines by the Application of Window Partitioning Technique to the Waveform Relaxation Approach (Special Section on Nonlinear Theory and Its Applications)
- Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform (Special Section on Selected Papers from the 11th Workshop on Circuits and Systems in Karuizawa)
- A Neural Net Approach to Discrete Walsh Transform (Special Section of Letters Selected from the 1994 IEICE Spring Conference)
- Dynamically Overlapped Partitioning Technique to Implement Waveform Relaxation Simulation of Bipolar Circuits
- Design and Simulation of Neural Network Digital Sequential Circuits (Special Section of Papers Selected from JTC-CSCC'93)