Introduction To The Theory Of Neural ComputationCRC Press, 8 бер. 2018 р. - 352 стор. Comprehensive introduction to the neural network models currently under intensive study for computational applications. It also provides coverage of neural network applications in a variety of problems of both theoretical and practical interest. |
Зміст
THREE Extensions of the Hopfield Model | |
FOUR Optimization Problems | |
FIVE Simple Perceptrons | |
SEVEN Recurrent Networks | |
EIGHT Unsupervised Hebbian Learning | |
NINE Unsupervised Competitive Learning | |
SIX MultiLayer Networks | |
TEN Formal Statistical Mechanics of Neural Networks | |
APPENDIX Statistical Mechanics | |
Bibliography | |
Інші видання - Показати все
Introduction To The Theory Of Neural Computation, Volume I John A Hertz,Anders Krogh,Richard G Palmer Перегляд фрагмента - 1991 |
Introduction To The Theory Of Neural Computation, Volume I John A Hertz,Anders Krogh,Richard G Palmer Перегляд фрагмента - 1991 |
Загальні терміни та фрази
algorithm applied approach appropriate architecture attractor average back-propagation binary Boltzmann machine competitive learning Conference on Neural context units continuous-valued convergence correlation cost function dynamical eigenvalues eigenvector energy function equations equilibrium error example feature mapping feed-forward feed-forward networks FIGURE gradient descent Grossberg h₁ Hebbian Hebbian learning hidden layer hidden units Hopfield IEEE implement input patterns input vector Kohonen learning rule linear matrix mean field minimize Networks San Diego Neural Computation Neural Networks Neural Networks San neurons nonlinear optimization output layer output units parameters perceptron possible principal component principal component analysis probability problem random receptive fields recurrent network reinforcement learning result S₁ Sejnowski sequence simple perceptron simulated annealing solution spin statistical mechanics stochastic subspace symmetric temperature term threshold Touretzky training set Travelling Salesman Problem unsupervised learning update V₁ values visible units w₁ weight vector zero