Neural network engineering in dynamic control systems
著者
書誌事項
Neural network engineering in dynamic control systems
（Advances in industrial control）
Springer, c1995
大学図書館所蔵 件 / 全31件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes bibliographical references and index
内容説明・目次
内容説明
This study evaluates the state of the art in the area of neural networks from the engineering perspective. The book examines ways of improving the engineering involved in neural network modelling and control, so that the theoretical power of learning systems can be harnessed for practical applications. The book seeks to answer a number of questions, such as which network architecture for which application? Can constructive learning algorithms capture the underlying dynamics while avoiding overfitting? How can we introduce a priori knowledge or models into neural networks? Can experimental design and active learning be used automatically to create "optimal" training sets? And finally, how can we validate a neural network model?
目次
- Neural approximation - a control perspective
- dynamic systems in neural networks
- adaptive neurocontrol of a certain class of MIMO discrete-time processes based on stability theory
- local model architectures for nonlinear modelling and control
- on ASMOD - an algorithm for empirical modelling using spline functions
- semi-empirical modelling of nonlinear dynamics systems through identification of operating regimes and local models
- on interpolating memories of learning control
- construction and design of parsimonious neurofuzzy systems
- fast gradient-based off-line training of multilayer perseptrons
- Kohonen network as a classifier and predictor for the qualification of metal-oxide surfaces
- analysis and classification of energy requirement situations using Kohonen feature maps within a forecasting system
- a radial basis function network model for adaptive control of drying oven temperature
- hierarchical competitive net architecture.
「Nielsen BookData」 より