Artificial Neural Network based on Simulated Evolution and its Application to Estimation of Landslide
スポンサーリンク
概要
- 論文の詳細を見る
The conventional steepest descent method in the back propagation process of an artificial neural network (ANN) is replaced by Simulated Evolution algorithm. This is called SimE-ANN and is applied to the estimation of landslide. In the experimental results, the errors of displacement and resistance of the piles in SimE-ANN, which are the outputs of landslide estimation problem, are 17% and 58% smaller than those of the conventional ANN, respectively. Moreover, the CPU time for the learning is 99% reduced.
- 2011-05-10
著者
-
Yoichi Shiraishi
Department Of Production Science And Technology Gunma University
-
Yao Zhou
Department Of Production Science And Technology Gunma University
-
Yoichi Shiraishi
Department Of Production Science & Technology Gunma University Gunma Japan
関連論文
- Simulation Based Design for Inverter Power Supply
- Matlab Simulink Modelling of the DC-AC Inverter
- Artificial Neural Network based on Simulated Evolution and its Application to Estimation of Landslide
- Multi Constrained Route Optimization for Electric Vehicles (EVs) using Simulated Evolution (SimE)
- Simulation based Design for Inverter Power Supply
- A Novel Particle Swarm Optimization based Algorithm for Path Optimization in Embedded Systems
- Memory-efficient Genetic Algorithm for Path Optimization in Embedded Systems