📌 Deep Learning

Deep Learning is a subset of Machine Learning that uses artificial neural networks with multiple layers to automatically learn complex patterns and representations from data.

📊 Types of Machine Learning 🔹 Supervised Learning

In supervised learning, the algorithm is trained using input data along with target labels (desired outputs). The model learns to produce outputs as close as possible to the targets.

Objective Function: Loss (Cost/Error) Function

Goal: Minimize loss to improve accuracy

Common Methods:

Regression

Classification

🔹 Unsupervised Learning

In unsupervised learning, the model is provided only with input data, without any target labels. It discovers hidden patterns or structures in the data.

Example: Clustering countries based on financial data into groups such as Developed, Developing, or Stagnating.

Common Methods:

Clustering

🔹 Reinforcement Learning

Reinforcement learning focuses on learning through interaction with an environment. The algorithm takes actions and receives rewards or penalties, learning to maximize total reward.

Objective Function: Reward Function

Goal: Maximize reward

Example: A computer learning to play Super Mario, where a higher score indicates better performance.

Common Methods:

Decision Process

Reward System

🧠 Neural Networks in Deep Learning

Training a neural network involves four key components:

Data – Input used for training

Model – Neural network architecture

Objective Function – Measures model performance

Optimization Algorithm – Updates model weights

Objective Function

The objective function evaluates how well the model’s predictions match the correct values.

Types of Objective Functions:

Loss Function (Supervised Learning)

Reward Function (Reinforcement Learning)