Neural Networks for Statistical Modeling |
Contents
Mapping Functions | 1 |
Basic Concepts | 59 |
Error Derivatives | 65 |
Copyright | |
13 other sections not shown
Common terms and phrases
a₁ accuracy Adaline adaptive learning rates approach average axis backpropagation bias weight boundary calculate class variables Connectionism curve decreases dependent variable disk dOut(j epochs equation error derivatives error surface error with respect forward pass Geoffrey Hinton gradient descent graph Grossberg hidden layer hidden node's output hidden nodes hidden units hids illustration increases independent input nodes limit linear regression logistic function mapping function mean squared error method of temporal modeling technique momentum network output network's error Neural Networks neuron node's weighted noise number of examples number of hidden number of inputs optimal output node output surface overfitting parameters pattern perceptron predict problem produce quantitative variables quantities ravine recurrent network relationship represent representation Rumelhart sigmoid function SINGLE DIM slope statistical modeling steepest descent stop training subroutine sum of inputs target function target output temporal differences training data training sample validation sample weight changes Weight Point weighted sum x₁ ду