Module 3: Neural Networks

Welcome back! In this module, Maria Chen will teach you how artificial neurons work together to recognize patterns - the foundation of modern AI.

What You'll Learn:

  • 🧠 How biological neurons inspired artificial ones
  • ⚡ Inputs, weights, and activation functions
  • 🔗 How neurons connect in layers
  • 🎯 How training adjusts weights to learn

From Biology to Technology

Neural networks are inspired by the human brain. Let's explore the connection!

Scroll down to explore
🧠
Key Insight: Your brain has about 86 billion neurons connected by trillions of synapses. Artificial neural networks are simplified versions of this biological system!

The Brain-AI Connection

Click each card to discover how biological concepts inspired AI.

🧠
Biological Neuron
Click to learn more
⚡
Signal Transmission
Click to learn more
📚
Learning & Memory
Click to learn more
🔗
Network Structure
Click to learn more

Click each concept (0/4 explored)

Inside an Artificial Neuron

An artificial neuron is a computational unit inspired by biology. It performs a mathematical calculation to process data.

Scroll down to explore
⚡
The Basic Formula: An artificial neuron takes inputs, multiplies each by a weight, adds them up, and decides whether to "fire" based on a threshold.

Neuron Components

Click each card to understand the parts of an artificial neuron.

📥
Inputs
Click to learn more
⚖
Weights
Click to learn more
➕
Weighted Sum
Click to learn more
💡
Activation
Click to learn more

Click each component (0/4 explored)

Neuron Simulator

Now let's see a neuron in action! Adjust the inputs and watch how the neuron decides whether to fire.

Scroll down to interact
Input 1 5
Weight: 0.6
Input 2 3
Weight: 0.4
Sum: 0 ?
→
Not Firing
Threshold: 5.0

The neuron fires when the weighted sum exceeds the threshold

Try it: Adjust the sliders above to see how changing inputs affects whether the neuron fires!

Make the neuron fire and not fire to continue (0/2 states seen)

Neurons Working Together

One neuron alone can't do much. The power comes when many neurons work together in layers!

Scroll down to explore
🔗
Key Concept: Neural networks have layers: an input layer, one or more hidden layers, and an output layer. Each layer transforms the data in a different way.

Network Layers

Click each card to understand the different types of layers.

📥
Input Layer
Click to learn more
🧠
Hidden Layers
Click to learn more
📦
Output Layer
Click to learn more

Click each layer type (0/3 explored)

Input
x1
x2
x3
⟶
Hidden
⟶
Output
y1
y2

How Neural Networks Learn

Networks learn by adjusting their weights based on how wrong their predictions are.

Scroll down to explore
🎯
Training Loop: Make a prediction → Compare to correct answer → Adjust weights → Repeat thousands of times until accurate!

Training Concepts

Click each card to understand how networks learn.

→
Forward Pass
Click to learn more
📈
Loss Function
Click to learn more
←
Backpropagation
Click to learn more
🔄
Weight Update
Click to learn more

Click each concept (0/4 explored)

Neural Network Vocabulary

Let's make sure you know the key neural network terms! Match each term to its definition.

Scroll down to continue

How to play: Click a term on the left, then click its matching definition on the right.

Neural Network Terms
Weight
Activation Function
Hidden Layer
Backpropagation
Loss Function
Definitions
Layers between input and output that find patterns
Measures how wrong the network's prediction is
A number that determines input importance
Algorithm that adjusts weights based on errors
Decides if a neuron should fire or not
Match all 5 terms (0/5 matched)

Knowledge Check

Answer these questions to earn your Neural Network Certificate!

Scroll down to see all questions
🧠

Neural Network Certificate

AI Fundamentals Series - Module 3 Complete

Silver Level

Your Name

Has demonstrated understanding of neural network fundamentals including artificial neurons, layers, weights, activation functions, and the training process.

Scroll down to continue

What's Next?

In Module 4: Deep Learning, you'll discover why adding more layers makes AI so powerful!