Introduction to Deep Learning with Keras: Building and Training a Simple Neural Network

Goal : Understand the basic concepts of deep learning.

Learning Content : Neural network basics, Keras basics, and a hands‑on practice building a simple neural network with Keras.

Code Example :

import numpy as np
import pandas as pd
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.optimizers import Adam
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_iris

# Load example dataset (Iris)
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['target'] = iris.target
print(f"Example dataset:\n{df.head()}")

# Split dataset into training and test sets
X = df.drop('target', axis=1)
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print(f"Training features:\n{X_train.head()}")
print(f"Test features:\n{X_test.head()}")
print(f"Training labels:\n{y_train.head()}")
print(f"Test labels:\n{y_test.head()}")

# Standardize features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Define a simple neural network model
model = Sequential()
model.add(Dense(10, input_dim=4, activation='relu'))  # Input layer and first hidden layer
model.add(Dense(10, activation='relu'))              # Second hidden layer
model.add(Dense(3, activation='softmax'))            # Output layer
model.summary()

# Compile the model
model.compile(optimizer=Adam(learning_rate=0.01), loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Train the model
history = model.fit(X_train_scaled, y_train, epochs=50, batch_size=10, validation_split=0.2)

# Evaluate the model on the test set
loss, accuracy = model.evaluate(X_test_scaled, y_test)
print(f"Test loss: {loss:.4f}")
print(f"Test accuracy: {accuracy:.4f}")

# Plot training and validation loss and accuracy
import matplotlib.pyplot as plt
plt.figure(figsize=(12, 4))
plt.subplot(1, 2, 1)
plt.plot(history.history['loss'], label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.title('Training and Validation Loss')
plt.subplot(1, 2, 2)
plt.plot(history.history['accuracy'], label='Training Accuracy')
plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.title('Training and Validation Accuracy')
plt.show()

# Predict with the model
y_pred = model.predict(X_test_scaled)
y_pred_classes = np.argmax(y_pred, axis=1)
print(f"First few predictions:\n{y_pred_classes[:10]}")
print(f"First few true labels:\n{y_test[:10].values}")

Practice : The same code is repeated as a hands‑on exercise, allowing learners to run the full workflow from data loading to model evaluation and prediction.

Summary : After completing the exercise, you should understand neural network fundamentals and be able to build, train, evaluate, and visualize a simple Keras model, ready to apply these skills to real projects.