Machine Learning & AI

Intermediate

Perceptron Update

The original learning rule that nudges weights when a prediction is wrong.

Formula

\mathbf{w} := \mathbf{w} + \eta\,(y-\hat{y})\,\mathbf{x}

Variables

\etaLearning rate

yTrue label

\hat{y}Prediction

\mathbf{x}Input

Example

Correct prediction: no update

Did You Know?

Rosenblatt built the Perceptron in 1958 as physical hardware — the ancestor of neural networks.

perceptron neural network history

Share this formula

More in Machine Learning & AI

Linear Regression Model

Predicts a continuous value as a weighted sum of input features plus a bias.

Gradient Descent Update

Iteratively moves parameters in the direction that most reduces the loss.

ReLU Activation

Rectified Linear Unit: outputs the input if positive, else zero.

Leaky ReLU

A ReLU variant that lets a small gradient flow for negative inputs.

Tanh Activation

Squashes input to the range (-1, 1); zero-centred activation.

Softmax

Turns a vector of scores into a probability distribution that sums to 1.