Python Machine Learning: Building Your First Neural Network

Introduction to Neural Networks

Neural networks are computing systems inspired by biological neural networks. Let us build one using Python and TensorFlow.

Installation

pip install tensorflow numpy pandas scikit-learn

Basic Neural Network

import tensorflow as tf
from tensorflow import keras
import numpy as np

# Load dataset
(X_train, y_train), (X_test, y_test) = keras.datasets.mnist.load_data()

# Preprocess
X_train = X_train.reshape(-1, 784) / 255.0
X_test = X_test.reshape(-1, 784) / 255.0

# Build model
model = keras.Sequential([
    keras.layers.Dense(128, activation="relu"),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(10, activation="softmax")
])

# Compile
model.compile(
    optimizer="adam",
    loss="sparse_categorical_crossentropy",
    metrics=["accuracy"]
)

# Train
model.fit(X_train, y_train, epochs=5, batch_size=32)

# Evaluate
test_loss, test_acc = model.evaluate(X_test, y_test)
print(f"Test accuracy: {test_acc:.4f}")

Understanding the Code

1. Data Loading: We use MNIST dataset (handwritten digits)
2. Preprocessing: Normalize pixel values to 0-1
3. Model Architecture: Input → Hidden → Output layers
4. Training: 5 epochs with batch size 32