 |
|
What people are saying - Write a reviewUser ratings
User Review - Flag as inappropriate This is an excellent book with lastest adcances fully reflected. User Review - Flag as inappropriate ok Related books
Other editions - View all
Common terms and phrasesannealing applied approximation attractor back-propagation back-propagation algorithm Boltzmann machine Chapter computational condition convergence cost function covariance matrix data points defined denote derivative described desired response differential entropy dimensionality discussed distribution dynamic programming dynamic system eigenvalue equation error estimate examples feedback FIGURE formula Gaussian gradient hidden layer hidden neurons Hopfield input space input vector input–output iteration Kalman filter kernel kernel PCA Kullback–Leibler divergence learning algorithm learning-rate parameter least-squares linear LMS algorithm Lyapunov Markov chain method minimize multilayer perceptron mutual information neural network neuron nodes noise nonlinear observation optimal output layer particle filter pattern performance probability density function problem pX(x random variable random vector RBF network recurrent network regularization respect result Section self-organizing self-organizing map shown signal statistical stochastic supervised learning support vector machine synaptic weights theorem theory tion training sample update weight vector zero References to this bookFrom other books
From Google ScholarAn Information-Maximization Approach to Blind Separation and Blind ...Anthony J Bell, Terrence J Sejnowski - 1995 - Neural Computation Statistical Pattern Recognition: A Review2000 - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Alignment by Maximization of Mutual InformationPaul Viola, William M Wells III - 1997 - International Journal of Computer Vision A tutorial on support vector regressionAlex J Smola, Bernhard Schölkopf - 2004 - Statistics and Computing Bibliographic information
|
