델타 규칙(Delta Rule)

by 오파님 2018. 11. 7. 15:50

In machine learning, the Delta rule is a gradient descent learning rule for updating the weights of the inputs to artificial neurons in a single-layer neural network. It is a special case of the more general backpropagation algorithm. For a neuron with activation function , the delta rule for weight is given by

$\Delta w_{ji}=\alpha (t_{j}-y_{j})g'(h_{j})x_{i}$ ,