Artificial Neural Networks: Theory and Applications
This comprehensive tutorial on artifical neural networks covers all the important neural network architectures as well as the most recent theory--e.g., pattern recognition, statistical theory, and other mathematical prerequisites. A broad range of applications is provided for each of the architectures.
What people are saying - Write a review
Applications of Multilayer Feedforward Networks with
The Neocognitron Network
Characteristics of Artificial Networks
14 other sections not shown
activation functions ADALINE adaptive ANN architectures annealing applications associative memory attractor autoassociative backpropagation behavior binary Boltzmann machine cells chaotic chapter classification computed connections convergence defined Delta Rule denote derivative described dimension dynamics entropy equation error surface estimate feedback feedforward feedforward networks fuzzy set given gradient descent Hebbian learning heteroassociative hidden layer hidden units Hopfield networks illustrated in Figure initial input pattern input vector iterations learning algorithm learning methods learning process linear linearly Lyapunov exponents mapping matrix minimize MLFF networks mutual information neocognitron network architecture neural network neurons nonlinear optimization output nodes output pattern output units parameters performance predict problem random variable recurrent networks retrieval sample sigmoid sigmoid function signal simulated simulated annealing single solution space supervised learning target theorem training patterns training set types update rule weight adjustment weight matrix weight values Widrow zero