What is ML
To follow the code in this course, it is useful to complete the following courses first, unless these topics are already familiar:
Machine learning (ML) is an approach to programming where computers learn from data to solve a task instead of being given explicit instructions.
Consider the example of a spam/ham (not spam) classifier.
Building such a system with a traditional programming approach (without ML) is difficult, as it requires writing explicit rules, even manually compiling a list of spam words.
With machine learning, the model is trained on many examples of spam and ham emails and learns the distinguishing patterns on its own.
The data provided for training is called the training set. In this case, it consists of emails already labeled as spam or ham, which enables the model to capture the characteristics of both categories.
After training, the model is evaluated using a test set - a separate collection of labeled emails. This step checks how well the model generalizes to new, unseen data.
Thanks for your feedback!
Ask AI
Ask AI
Ask anything or try one of the suggested questions to begin our chat
Can you explain more about how the training and test sets are created?
What are some common features used to classify emails as spam or ham?
How does the model actually learn to distinguish between spam and ham?
Awesome!
Completion rate improved to 3.13What is ML
Swipe to show menu
To follow the code in this course, it is useful to complete the following courses first, unless these topics are already familiar:
Machine learning (ML) is an approach to programming where computers learn from data to solve a task instead of being given explicit instructions.
Consider the example of a spam/ham (not spam) classifier.
Building such a system with a traditional programming approach (without ML) is difficult, as it requires writing explicit rules, even manually compiling a list of spam words.
With machine learning, the model is trained on many examples of spam and ham emails and learns the distinguishing patterns on its own.
The data provided for training is called the training set. In this case, it consists of emails already labeled as spam or ham, which enables the model to capture the characteristics of both categories.
After training, the model is evaluated using a test set - a separate collection of labeled emails. This step checks how well the model generalizes to new, unseen data.
Thanks for your feedback!
