Standard error-back-propagation

B. Standard Error-Back-Propagation Training Routine... 

In a standard back-propagation scheme, updating the weights is done iteratively. The weights for each connection are initially randomized when the neural network undergoes training. Then the error between the target output and the network predicted output are back-propa-... 

The overall process is repeated many times until the ANN converges to a point where the weights do not change and a model is obtained that predicts (classifies) correctly all the standards [38]. Frequently, convergence is not reached and a preset threshold error is allowed for. Figure 5.5 presents a general scheme with some more details of the back-propagation process. 

Appendixes Tables of solubility products, acid dissociation constants (updated to 2001 values), redox potentials, and formation constants appear at the back of the book. You will also find discussions of logarithms and exponents, equations of a straight line, propagation of error, balancing redox equations, normality, and analytical standards. 

Appendixes and Endpapers. Included in the appendixes are an updated guide to the literature of analytical chemistry, tables of chemical constants, electrode potentials, and recommended compounds for the preparation of standard materials sections on the use of logarithms and exponential notation, and on normality and equivalents (terms that are not used in the text itself) and a derivation of the propagation of error equations. The inside front and back covers of this book provide a full-color chart of chemical indicators, a table of molar masses of com-... 

---