Andere Kunden interessierten sich auch für
![Using Neural Networks for Estimating Cruise Missile Reliability]( "Using Neural Networks for Estimating Cruise Missile Reliability")
Using Neural Networks for Estimating Cruise Missile Reliability59,99 €![Combat Identification Modeling Using Neural Networks Techniques]( "Combat Identification Modeling Using Neural Networks Techniques")
Combat Identification Modeling Using Neural Networks Techniques59,99 €![Image Fusion Using Autoassociative-Heteroassociative Neural Networks]( "Image Fusion Using Autoassociative-Heteroassociative Neural Networks")
Image Fusion Using Autoassociative-Heteroassociative Neural Networks59,99 €![Selection of Psychophysiological Features Across Subjects for Classifying Workload Using Artificial Neural Networks]( "Selection of Psychophysiological Features Across Subjects for Classifying Workload Using Artificial Neural Networks")
Selection of Psychophysiological Features Across Subjects for Classifying Workload Using Artificial Neural Networks59,99 €![An Integrated Architecture and Feature Selection Algorithm for Radial Basis Neural Networks]( "An Integrated Architecture and Feature Selection Algorithm for Radial Basis Neural Networks")
An Integrated Architecture and Feature Selection Algorithm for Radial Basis Neural Networks59,99 €![Autonomous Defensive Space Control via On-Board Artificial Neural Networks]( "Autonomous Defensive Space Control via On-Board Artificial Neural Networks")
Autonomous Defensive Space Control via On-Board Artificial Neural Networks59,99 €![Autonomous Defensive Space Control Via On-Board Artificial Neural Networks]( "Autonomous Defensive Space Control Via On-Board Artificial Neural Networks")
Autonomous Defensive Space Control Via On-Board Artificial Neural Networks59,99 €
Feed-forward neural networks executing back propagation are a common tool for regression and pattern recognition problems. These types of neural networks can adjust themselves to data without any prior knowledge of the input data. Feed-forward neural networks with a hidden layer can approximate any function with arbitrary accuracy. In this research, the upper layer weights of the neural network structure are used to determine an effective middle layer structure and when to terminate training. By combining these two techniques with signal-to-noise ratio feature selection, a process is created to construct an efficient neural network structure. The results of this research show that for data sets tested thus far, these methods yield efficient neural network structure in minimal training time. Data sets used include an XOR data set, Fisher's Iris problem, a financial industry data set, among others.