Neural Computing: Theory and PracticeThis book for nonspecialists clearly explains major algorithms and demystifies the rigorous math involved in neural networks. Uses a step-by-step approach for implementing commonly used paradigms. |
Contents
Introduction | 1 |
Fundamentals of Artificial Neural Networks | 11 |
Perceptrons | 27 |
Copyright | |
10 other sections not shown
Common terms and phrases
activation function array artificial neural networks associative memory axon B₁ backpropagation binary biological brain calculated Cauchy Cauchy distribution cell body cognitron column comparison layer competition region complex cell components configuration convergence counterpropagation network desired output dot product energy error example excitatory Figure firing global minimum Grossberg layer Hebbian learning hidden layer Hopfield Hopfield net Hopfield network human IEEE input layer input pattern input vector Kohonen layer Kohonen neuron lateral inhibition layer neuron linear matrix multiplication method modulator multiplied neocognitron network weights objective function operation Optical neural networks output layer output of neuron output vector perceptron perform photodetector problem produce recognition layer recognition-layer neuron recurrent networks response result set of inputs signal simple cell single-layer networks stable stored pattern thereby threshold tion training algorithm training process training set weight adjustment weight change weight mask weight matrix weight vectors Widrow Wpq,k(n zero