01. What is Machine Learning? Understanding the Core Concepts

1. What is Machine Learning?

• Machine Learning is a technology where computers learn patterns from data (experience) without explicitly programmed rules.
• “Learning” means that a program improves its performance on a task through experience.
  • Example: Classifying spam emails

---

2. Why Has Machine Learning Become Possible?

• An explosive increase in available data
• Significant advancements in computing power
• Although machine learning has existed for decades, it has only become truly practical since the 2010s, thanks to the maturity of data availability and computational resources.

---

3. AI, Big Data, and Machine Learning: How Are They Related?

• Artificial Intelligence (AI)
  → The field of making computer systems think and act like humans
• Machine Learning (ML)
  → A key approach to achieving AI
• Deep Learning
  → A subset of machine learning that uses multiple deep layers to learn complex patterns
• Big Data
  → The field of collecting, storing, and analyzing massive amounts of data to extract valuable insights

---

4. Supervised vs. Unsupervised Learning in Deep Learning

Supervised Learning

• The training data comes with labels, and the goal is to predict those correct outputs.
• It’s more intuitive and widely used in practice.

Classification	Regression
Categorizes data into two or more discrete groups	Predicts continuous numerical values
Example: Spam email classification	Example: Predicting apartment prices

---

Unsupervised Learning

• There are no predefined labels.
• The algorithm discovers patterns or groups within the data on its own.

---

5. The k-NN Algorithm

• Finds the k nearest data points and predicts outcomes based on their values.
• k-NN is one of the machine learning algorithms.
• The more data (experience) the model has, the better its performance — a key feature of machine learning.
• Example: Predicting the survival of Titanic passengers (a classification problem in supervised learning)

---

6. Mathematics Behind Machine Learning

• Machine learning combines computer science and mathematics.
• A minimum understanding of math is essential for choosing the right algorithms and optimizing code.
• Key mathematical areas in machine learning include:
  • Linear Algebra: Used to handle large data efficiently through matrices
  • Calculus: Helps in optimizing models
  • Statistics: Identifies trends in data and supports predictions
  • Probability Theory: Deals with evaluating and reasoning about uncertainty

---

In One Sentence
Machine learning is a technology that enables computers to improve performance through experience using large-scale data, forming a core part of today’s AI and big data era.

---