A one-layer network trained by reducing error in its linear output.
ADALINE is like a picky DJ with a volume knob. If the music is three clicks too loud, it turns down three clicks.
It shows up in simple filters and classifiers. It keeps changing its weights to shrink the error.
Widrow-Hoff Learning Rule (Least Mean Squares Rule)
ADALINE is classically trained with the Widrow-Hoff Learning Rule.
Perceptron
ADALINE looks like a Perceptron, but it learns from the size of the error.
Gradient Descent
ADALINE updates its weights like repeated steps of Gradient Descent.
Neural-network
ADALINE is a classic early one-layer Neural-network.