Machine Learning

What is Machine Learning?

Definition

Machine learning is defined as the field of study that gives computers the ability to learn without being explicitly programmed. This definition is attributed to Arthur Samuel.

Historical Example

Arthur Samuel created a checkers playing program in the 1950s that demonstrated early machine learning principles:

• Samuel himself wasn’t a very good checkers player
• He programmed the computer to play tens of thousands of games against itself
• By observing which board positions led to wins versus losses, the program learned over time
• The computer gained patience to play extensive games, accumulating enough experience to become better than Samuel himself
• The program learned to seek good positions and avoid bad ones

Tip

Key Insight: The more opportunities you give a learning algorithm to learn, the better it will perform.

Main Types of Machine Learning

The two primary types of machine learning are:

• Supervised Learning: The most widely used form in real-world applications with rapid advancements
• Unsupervised Learning: Another major category covered later in the specialization

Course Structure

This specialization contains three courses:

• Courses 1 & 2: Focus on supervised learning
• Course 3: Covers unsupervised learning, recommender systems, and reinforcement learning

The most commonly used learning algorithms today are supervised learning, unsupervised learning, and recommender systems.

Practical Application Focus

Beyond learning algorithms, this course emphasizes practical advice for applying machine learning effectively. Having great tools is important, but knowing how to apply them properly is equally or more crucial.

Common challenges in industry include experienced teams spending months on approaches that won’t work. This course teaches best practices to avoid such pitfalls and helps develop skills like the most experienced machine learning engineers.

Learning Objectives

• Understand the fundamental definition of machine learning
• Learn about the main types of machine learning
• Gain practical skills for implementing machine learning systems effectively
• Develop expertise in applying machine learning tools correctly

The course aims to prepare students as skilled practitioners who can design and build serious machine learning systems, making them part of the rare group of people with this valuable expertise.