Exploratory Analysis of Metallurgical Process Data with Neural Networks and Related Methods
Elsevier, 2002. gada 19. apr. - 386 lappuses
This volume is concerned with the analysis and interpretation of multivariate measurements commonly found in the mineral and metallurgical industries, with the emphasis on the use of neural networks.
1.5. rezultāts no 85.
... ill-defined systems are concerned. Many parallels can be drawn between the development of knowledge-based systems and that of neural networks.
The output of the neuron can be expressed as follows. z= f(X="wix), or z = f(w'x) (1.1) where w is the weight vector of the neural node, defined as ...
... and the learning signal of the rule is defined as r=[d f(w'x)]f(w"x) (1.17) The term f(w'x) is the derivative of the activation function f(w's).
The cost function (E) can be defined in terms of the discrepancies between the outputs of the neural network and the desired or target output values.
These weights form the crux of the model, in that they define a distributed internal relationship between the. Training Rules 19 1.6. NEURAL NETWORK MODELS.
Lietotāju komentāri - Rakstīt atsauksmi
CHAPTER 3 LATENT VARIABLE METHODS
CHAPTER 4 REGRESSION MODELS
CHAPTER 5 TOPOGRAPHICAL MAPPINGS WITH NEURAL NETWORKS
CHAPTER 6 CLUSTER ANALYSIS
CHAPTER 7 EXTRACTION OF RULES FROM DATA WITH NEURAL NETWORKS
CHAPTER 8 INTRODUCTION TO THE MODELLING OF DYNAMIC SYSTEMSCHAPTER
DYNAMIC SYSTEMS ANALYSIS AND MODELLING
CHAPTER 10 EMBEDDING OF MULTIVARIATE DYNAMIC PROCESS SYSTEMS
CHAPTER 11 FROM EXPLORATORY DATA ANALYSIS TO DECISION SUPPORT AND PROCESS CONTROL
Citi izdevumi - Skatīt visu
Exploratory Analysis of Metallurgical Process Data with Neural Networks and ...
Ierobežota priekšskatīšana - 2002