Neural NetworksMacmillan Education, 1991 - 145 pages The term neural networks is used to describe a number of different models intended to imitate some of the functions of the human brain, using certain of its basic structures. The authors aim to convey an intuitive and practical understanding of the topic and to provide the foundations necessary before undertaking further study. To this end, the first part of the book is devoted to a description of biological foundations. Biology is the source of study of neural networks and it seems probable that it will continue to provide a source of essential ideas. Following this introduction, a general model for neural networks is presented and a number of today's most important models are studied. Lastly, a number of real applications are discussed. |
Table des matières
Neural Models | 19 |
Multilayer Neural Networks | 36 |
The Hopfield Model | 63 |
Droits d'auteur | |
5 autres sections non affichées
Expressions et termes fréquents
action potential activation function algorithm application architecture associative cells axon back-propagation behaviour Boltzmann machine boolean BPSK brain calculation characteristics classes classification connection weights connections between neurons consider convergence decision cell defined dendrites described error external world full set gives gradient descent Hebb rule hidden layers hidden units histograms Hopfield model Hopfield network implement input signal input vector introduced learning algorithm learning phase learning process learning rule matrix memory method minimising modified modulation multi-layer nerve cells nervous system NETTalk neural computer neural networks neuroreceptors noise operation orthogonal output layer output neurons parallel particular pattern recognition perceptron potential preprocessing presented problem processor propagation receptors representation represented retina set of examples shown in figure shows sigmoid function simple cells simulated annealing solution stable stochastic synapses synthetic neuron threshold neuron training set transputer travelling salesman problem variable verbs weight vector weighted sum Widrow-Hoff rule