A Single Artificial Neuron

Lesson notes

Overview

Weighted inputs plus a bias pass through an activation function to give an output. This topic is rated intermediate and is number 47 of 117 in Computer Science. Builds on the basics with relationships, methods and trade-offs.

What you are seeing

The panel above shows an interactive animation of the idea. Every slider changes one quantity so you can see its effect on the outcome. The animation is drawn live from the model, so everything you see responds to the sliders. Press Space to pause, use Restart to replay from the start, and change the speed to slow down quick events.

In depth

An artificial neuron computes a weighted sum of its inputs plus a bias and passes the result through an activation function: y = σ(w·x + b). The weights say how much each input matters, the bias shifts the threshold, and the activation function, such as a sigmoid or ReLU, gives non-linearity. A single neuron can learn to separate two classes by a straight line, as the perceptron does. Networks stack many of them in layers.

Reading the relationship

The expression "y = σ(w·x + b)" is a compact summary of the idea. It uses the symbols y, σ, w, x, b; name what each one stands for before you start. Then use the sliders to see how changing one quantity changes the others.

A guided exploration

1. Run the animation once with the default settings and describe in words what happens. 2. Change one slider at a time and note which quantity responds most. 3. Push each slider to its extreme and decide whether the result still makes sense.

Try this

Predict the outcome first, then test extreme slider values to find where the pattern changes or breaks.

Common pitfalls

Test small inputs by hand and then the largest ones. Off-by-one errors and forgetting how cost grows with input size are the most common traps.

How it connects

It builds on “Recursive Trees”, the topic before it in Computer Science. Once you are comfortable, continue with “Gradient Descent”.

Why it matters

Computing ideas decide how fast, how safely and how well software can solve problems.