Your First Neural Network

In this section, you’ll build your first complete Keras model using a real dataset: MNIST handwritten digits.

This section demonstrates all core steps you'll use in every deep learning project:

1. Load data
2. Prepare data
3. Build model
4. Compile model
5. Train model
6. Evaluate model
7. Predict using model

Load the MNIST Dataset

MNIST is built into Keras:

MNIST consists of:

• 60,000 training images
• 10,000 test images
• Each image is 28×28 grayscale
• Each label is an integer from 0 to 9

Inspect shapes:

Preprocess the Data

Neural networks work best with scaled data.

Convert pixel values (0–255) to floats (0–1):

Flatten images (28×28 → 784)

Our first model is a simple Dense network, so flattening is required.

Later sections (CNNs) will use unflattened images.

Build the Model

Use a basic Sequential API MLP (multi-layer perceptron):

Explanation:

• 128 hidden units → moderate-sized hidden layer
• ReLU activation → standard for hidden layers
• Softmax output → required for multi-class classification

Compile the Model

Compile defines:

• Loss function
• Optimiser
• Metrics

Why these choices?

• Adam: good general-purpose optimizer
• Sparse categorical crossentropy: correct loss for multi-class integer labels
• Accuracy: practical metric for classification

Train the Model

Training is done via .fit().

What each parameter means:

• batch_size=32 - Standard mini-batch gradient descent batch size
• epochs=5 - Full passes through the training data
• validation_split=0.1 - Reserves 10% of training data for validation monitoring

Training output shows:

• Loss
• Accuracy
• Validation loss
• Validation accuracy

Evaluate the Model

MNIST typically gives:

Making Predictions

Predict class probabilities:

Predict most likely classes:

Compare with true labels:

Visualising a Prediction

Understanding the Training History

The .fit() method returns a history object containing training curves:

Common keys:

• loss
• accuracy
• val_loss
• val_accuracy

Example plotting accuracy:

The Full Script (Complete Working Example)