💚

Beginner-Friendly Topic

Take your time - it's perfectly normal to re-read this topic 2-3 times. Try the interactive code editor below to run code yourself. Use the Q&A section to check your understanding before moving on. You've got this! 🚀

What is a Neural Network?

A neural network is a system of connected mathematical units that work together to recognize patterns and make decisions. It is inspired by the structure of the brain, but it is a mathematical tool, not a biological one.

12 min•By Priygop Team•Updated 2026

The Brain Analogy

Your brain contains about 86 billion neurons. Each neuron connects to thousands of others. When you see a cat, signals travel through chains of neurons, and your brain recognizes the pattern as a cat.

An artificial neural network is a simplified mathematical version of this idea. Instead of billions of neurons, it has hundreds or millions of simple mathematical units. Instead of electrical signals, it passes numbers through mathematical calculations.

The key insight: by connecting many simple units together in layers, the network can recognize very complex patterns.

Diagram

Loading diagram…

Deep Learning ⊂ Machine Learning ⊂ Artificial Intelligence

The Structure of a Neural Network

Input layer: receives raw data (pixel values, numbers, text tokens)
Hidden layers: process information through mathematical operations
Output layer: produces the final result (a category, a number, a word)
Each layer is made of neurons (mathematical units)
Each neuron connects to neurons in the next layer
The connections have weights that determine how strongly signals are passed

A Neural Network Illustrated

# Neural network structure visualized in text
# Input layer -> Hidden layer -> Output layer

def draw_network():
    print("Simple Neural Network Structure:")
    print()
    print("Input Layer      Hidden Layer     Output Layer")
    print("(receives data)  (finds patterns) (makes decision)")
    print()
    print("   [Input 1] ---\")
    print("                 --> [Neuron A] --\")
    print("   [Input 2] ---/                 --> [Output]")
    print("                 --> [Neuron B] --/")
    print("   [Input 3] ---/")
    print()
    print("Each arrow represents a weighted connection.")
    print("The network learns the correct weights from training data.")
    print()

draw_network()

# A simple example: 3 inputs, 1 output
inputs = [0.5, 0.8, 0.3]          # some feature values
weights = [0.4, 0.6, 0.2]         # learned importance of each input
bias = 0.1

# The basic calculation every neuron does
weighted_sum = sum(x * w for x, w in zip(inputs, weights))
output = weighted_sum + bias

print(f"Inputs:  {inputs}")
print(f"Weights: {weights}")
print(f"Bias:    {bias}")
print(f"Output:  {output:.3f}")

Try It Yourself

Try It YourselfHTML

HTML Editor

✓ ValidTab = 2 spaces

# Change the inputs and weights to see how the output changes
inputs = [0.5, 0.8, 0.3]   # Try different values
weights = [0.4, 0.6, 0.2]  # Try different weights
bias = 0.1

weighted_sum = sum(x * w for x, w in zip(inputs, weights))
output = weighted_sum + bias

print(f"Weighted sum: {weighted_sum:.3f}")
print(f"Final output (with bias): {output:.3f}")
print()
print("Notice: if you increase a weight, that input has more influence")
print("If you increase an input value, the output increases proportionally")

Result

Click ▶ Run to see the result

Edit the code on the left, then click Run (Ctrl+Enter)

HTML|13 lines|513 chars|✓ Valid syntax

UTF-8

Quick Q&A

Key Takeaways

A neural network is a system of connected mathematical units that work together to recognize patterns and make decisions.
Input layer: receives raw data (pixel values, numbers, text tokens)
Hidden layers: process information through mathematical operations
Output layer: produces the final result (a category, a number, a word)

Topics in This Module