A Guide to Neural Computing Applications
Outlines how to make use of neural networks and teaches readers how to avoid some of the obvious, and not so obvious pitfalls which often lead to the unnecessary failure of objects. This unique book enables engineers to construct robust and meaningful non-linear models and classifiers, and benefits the more experienced practitioner.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Mathematical background for neural computing
Managing a neural computing project
Identifying applications and assessing their feasibility
7 other sections not shown
Other editions - View all
basis functions Chapter cluster centres content-addressable memories cross-validation data collection data set database deliverable system diabetes dimensionality encoded Equation error back-propagation algorithm error function Euclidean distance generalisation performance gradient descent hardware hidden units Hopfield networks implementation initialisations input data input patterns input space input variables input vectors iterations Kohonen map Kohonen's feature map large number learning rate linear classifier minimise multi-layer perceptron neural computing application neural computing projects neural network software neuron non-linear normalisation number of hidden number of inputs number of training optimisation output units packages partitions pattern recognition phase posterior probability pre-processing prediction procedure prototyping cycle random RBF network Section sigmoid sigmoid function sleep squared error supervised learning Tarassenko techniques test set topological ordering training and test training data training patterns training set validation and test validation set visualisation weight set weight update weight vectors