Neural Networks & Deep Learning

A neural network is a computing system inspired by the human brain. It consists of layers of interconnected "neurons" that process information. Deep Learning uses neural networks with many layers (hence "deep") to handle complex tasks like image recognition, speech translation, and natural language understanding.

• Input layer: receives the raw data (e.g., pixel values of an image).
• Hidden layers: extract patterns — edges, shapes, objects — layer by layer.
• Output layer: produces the final prediction (e.g., "cat" or "dog").
• Popular deep learning frameworks: TensorFlow (Google) and PyTorch (Meta).

💡 Practical Skill: Use TensorFlow Playground (online tool) to visually experiment with neural networks. No code needed — just drag layers and see how the network learns patterns.

# A minimal neural network using TensorFlow (Keras)# Install: pip install tensorflow import tensorflow as tfimport numpy as np # Simple dataset: learn the XOR logic gate# Input: [0,0], [0,1], [1,0], [1,1]# Output: 0, 1, 1, 0inputs = np.array([[0,0], [0,1], [1,0], [1,1]], dtype=float)outputs = np.array([[0], [1], [1], [0]], dtype=float) # Build the neural networkmodel = tf.keras.Sequential([    tf.keras.layers.Dense(4, activation='relu', input_shape=(2,)),    tf.keras.layers.Dense(1, activation='sigmoid')]) # Compile the modelmodel.compile(optimizer='adam', loss='mse') # Train the modelprint("Training the neural network...")model.fit(inputs, outputs, epochs=500, verbose=0)print("Training complete!") # Test predictionspredictions = model.predict(inputs, verbose=0)for i, inp in enumerate(inputs):    print(f"Input: {inp} => Predicted: {predictions[i][0]:.4f} (expected: {outputs[i][0]})")