Neurons, perceptrons and learning.
Learn through illustrated explanations, worked examples, practice questions and quick revision.
Before you start
Comfort with Boolean logic, coordinates, straight lines and weighted sums.
By the end: Explain a perceptron, update its weights and recognise why XOR needs a network.
Check the notation
x: input features; y: class label; w: weights; θ: threshold. With a constant input x₀ = 1, w₀ = −θ is the bias.
Study sections
Follow the order or choose a sectionFrom Brain Cells to the McCulloch–Pitts Neuron
Every deep learning model, from a phone’s face unlock to a chatbot, is built from one tiny unit: the artificial neuron . It is a very s…
02The Perceptron, Weights, Bias and Errors
The MP neuron treats every input the same and needs a human to choose θ. In real life some reasons matter more than others. The percept…
03Perceptron Learning Algorithm and Its Proof of Convergence
We don’t want to guess weights by hand. We want the perceptron to look at examples and fix itself whenever it makes a mistake. The Perc…
04XOR, Boolean Functions and the Power of a Network of Perceptrons
One perceptron draws one straight line. Some problems — even a tiny one called XOR — cannot be solved with one line. The fix is surpris…