Understand the Python Code

Our Simple Neuron

We will use the same example from the previous topic. Our neuron has two inputs, two weights, and one bias.

x1 = 2
x2 = 3

w1 = 0.5
w2 = 0.4

bias = 1

z = (x1 * w1) + (x2 * w2) + bias

print(z)

The output is:

3.2

Understand the Code Step by Step

Let's understand every important line instead of treating the code as something to memorize.

Step 1 — Define the Inputs

x1 = 2
x2 = 3

Here we create two input values.

In a real machine learning problem, these values could represent features from a dataset.

For example:

x1 = hours studied
x2 = attendance

We are using simple numbers here so we can clearly understand the neuron calculation.

Step 2 — Define the Weights

w1 = 0.5
w2 = 0.4

Each input has a corresponding weight.

So Python is storing the values that the neuron needs for its calculation.

Step 3 — Define the Bias

bias = 1

The bias is an additional value added after calculating the weighted inputs.

Step 4 — Calculate the Neuron Value

z = (x1 * w1) + (x2 * w2) + bias

This single line performs the main mathematical calculation.

Python replaces the variable names with their values.

z = (2 * 0.5) + (3 * 0.4) + 1

Now calculate each multiplication:

2 * 0.5 = 1.0
3 * 0.4 = 1.2

Then add them:

1.0 + 1.2 + 1 = 3.2

Step 5 — Print the Result

print(z)

The print() function displays the value stored inside z.

3.2

So the complete Python program calculates the weighted sum plus bias and displays the result.

What Each Variable Means

Putting the Calculation Into a Function

Instead of writing the calculation every time, we can create a Python function.

def neuron_output(x1, x2, w1, w2, bias):
    return (x1 * w1) + (x2 * w2) + bias


result = neuron_output(2, 3, 0.5, 0.4, 1)

print(result)

The output is:

3.2

How the Function Works

This line creates the function:

def neuron_output(x1, x2, w1, w2, bias):

The function expects five values:

Then this line performs the calculation:

return (x1 * w1) + (x2 * w2) + bias

Finally, we call the function:

result = neuron_output(2, 3, 0.5, 0.4, 1)

Python sends these values into the function:

x1 = 2
x2 = 3
w1 = 0.5
w2 = 0.4
bias = 1

The function calculates:

(2 × 0.5) + (3 × 0.4) + 1
= 3.2

Another Example

Let's change the values.

x1 = 5
x2 = 4

w1 = 0.2
w2 = 0.6

bias = 1

Calculate:

(5 × 0.2) + (4 × 0.6) + 1

= 1.0 + 2.4 + 1

= 4.4

Using the function:

result = neuron_output(5, 4, 0.2, 0.6, 1)

print(result)

Output:

4.4

This shows why using a function is useful. We can use different inputs, weights, and bias without rewriting the calculation.

Is This a Complete Neural Network?

No. This is only a very simple mathematical representation of one neuron.

A real neural network can contain many neurons, multiple layers, activation functions, and training algorithms.

The purpose of this example is to understand the calculation performed by an individual neuron before moving to larger neural networks.

Where Does the Activation Function Go?

Our current Python example calculates the value z, but it does not yet apply an activation function.

z = (x1 * w1) + (x2 * w2) + bias

Conceptually, the complete process is:

We will learn activation functions in the next lesson.

The Big Picture

x1 = 2
x2 = 3

w1 = 0.5
w2 = 0.4

bias = 1

z = (x1 * w1) + (x2 * w2) + bias

print(z)

The Python code is simply implementing the mathematics we already learned.