Delta rule

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 ${\displaystyle j\,}$ with activation function ${\displaystyle g(x)\,}$, the delta rule for ${\displaystyle j\,}$'s ${\displaystyle i\,}$th weight ${\displaystyle w_{ji}\,}$ is given by

...
Wikipedia