Introduction to Machine Learning

13 lessons0%

Resources

Lessons

What is Machine Learning?

Relationship between AI, Machine Learning, and Deep Learning

Types of Machine Learning Problems

Generalization in Machine Learning

Data in Machine Learning

What is a Machine Learning Model?

Loss Functions

How Models Learn

Overfitting and Underfitting

Regularization in Machine Learning

Why Multiple Algorithms Exist

Overview of ML Algorithms

The Machine Learning Workflow

Lesson 4 of 13

Premium lesson

Buy this course or get a membership to access all premium lessons.

One-time purchase - yours to keep forever

Access all premium courses and features with one membership

Already have access? Sign in here

AI Instructor

Hello, how can I help today?

Ask questions about this lesson and get instant answers.

Generalization in Machine Learning

The goal of machine learning is not to perform well on the data you have. It is to perform well on data you have not yet seen. This distinction is so important that it deserves its own name: generalization.

Why Generalization Matters

Consider a fraud detection model trained on historical transaction data. The model's value is not in correctly classifying transactions you already know are fraudulent. Those cases are already resolved. The model's value is in correctly identifying new fraudulent transactions as they occur in the future.