Lesson 1 of 3 · 14 min
What Is a Neural Network?
Meet the tiny decision machine. Inputs are sensors, weights are control knobs, and activation is the firing threshold that makes a neuron say 'yes!'
A brain made of knobs
Imagine a robot trying to decide if it should walk forward.
It has sensors — little eyes, bumpers and touch pads.
Each sensor sends in a number, and the network mixes those numbers to make a choice.
A neural network is just a pile of these simple decisions stacked together.
Inputs are sensors
A sensor might report 0.9 for 'wall very close' or 0.1 for 'path clear'.
The network never sees the world directly — only these numbers.
When we draw the network, each input is its own little circle, and it just holds a number.
Weights are control knobs
A weight turns an input up or down. It multiplies.
If a wide-open path matters a lot, its weight is large. If a sensor is noisy, its weight is tiny.
Worked example: an input of 2.0 with a weight of 0.5 becomes 2.0 × 0.5 = 1.0.
Turn that weight up to 3.0 and the same input becomes 6.0; set the weight to -1.0 and it flips to -2.0.
sum = (x₁ × w₁) + (x₂ × w₂) + b
A neuron multiplies each input by its weight, adds everything up, then adds the bias b.
From sum to boom: the threshold
After the sum, the activation function decides how hard the neuron fires.
ReLU ignores anything at or below zero and passes positives through: sum 1.2 → fire 1.2, sum -0.5 → fire 0.
Sigmoid squeezes the sum into 0 to 1 so it looks like a confidence: sum 1.2 → about 0.77.
That single number then becomes an input for the next layer.
Try it: trace one signal by hand
Signal Tracer — Follow the Numbers
Type inputs, click any connection to edit its weight, then watch the actual numbers flow: input → ×weight → sum + bias → activation → output.
This is the whole network with the lid off. Every line shows the signal travelling through it, every neuron shows its value, and you can rewire any weight or add hidden layers. Press Step to walk through one layer at a time.
Type the input values
Activation
Hidden layers
Connection weight
Click any line in the diagram to edit its weight.
Wait — what are Class A and Class B?
A network that sorts things is called a classifier, and the groups it sorts into are classes.
Imagine sorting animals: Class A = cats 🐱 (drawn as blue circles) and Class B = dogs 🐶 (orange crosses).
Every dot below is one animal described by two numbers, like ear roundness and tail length.
The network's job is to draw a line that puts cats on one side and dogs on the other — that line is the decision boundary.
Try it: turn the knobs
What Can a Tiny Brain Decide?
Drag the glowing point around. The background shows what the little network thinks: blue means 'yes' and orange means 'no'. Move the sliders to change what it believes.
Imagine sorting animals: Class A = cats 🐱 (blue circles), Class B = dogs 🐶 (orange crosses). Every dot on the map is one example. The network draws a line that tries to separate cats from dogs — drag the point to see which side it lands on.
Drag the point on the canvas to test the network anywhere.
Control knobs
Check yourself
Neural Network Basics
In our robot analogy, what do the *inputs* represent?