#5 Machine Learning Specialization [Course 1, Week 1, Lesson 2]  Summary and Q&A
TL;DR
In supervised learning, regression algorithms predict numbers while classification algorithms predict categories.
Key Insights
 ❓ Supervised learning consists of regression and classification algorithms.
 #️⃣ Regression algorithms predict numbers, while classification algorithms predict categories.
 ❓ Classification algorithms can have multiple output categories, not just two.
 🚱 Categories predicted by classification algorithms can be nonnumeric.
 🤱 Additional inputs can be used to improve the accuracy of classification algorithms in specific applications, such as breast cancer detection.
 😫 Classification algorithms predict a small finite set of possible output categories.
 #️⃣ Regression algorithms predict infinitely many possible numbers.
Transcript
so supervised learning algorithms learn to predict input output or X to Y mappings and in the last video you saw that regression algorithms which is a type of supervised learning algorithm learns to predict numbers out of infinitely many possible numbers there's a second major type of supervised learning algorithm called a classification algorithm ... Read More
Questions & Answers
Q: What is the difference between regression and classification in supervised learning?
In supervised learning, regression algorithms predict numbers, while classification algorithms predict categories. Regression predicts infinitely many possible numbers, while classification predicts a small finite set of possible categories.
Q: Can a classification algorithm have more than two output categories?
Yes, a classification algorithm can have more than two output categories. It can predict multiple types of cancer diagnoses, for example, if there are more than two possible types of cancer.
Q: Can classification algorithms predict nonnumeric categories?
Yes, classification algorithms can predict nonnumeric categories. For example, they can predict whether a picture is of a cat or a dog.
Q: What additional inputs can be used in classification algorithms for breast cancer detection?
In breast cancer detection, additional inputs like the thickness of the tumor, clump uniformity of the cell size, uniformity of the cell shape, and more can be used to improve the accuracy of the classification algorithm.
Summary & Key Takeaways

Supervised learning algorithms learn to predict inputoutput or X to Y mappings, with regression algorithms predicting numbers and classification algorithms predicting categories.

Classification algorithms are used in cases like breast cancer detection, where the goal is to classify tumors as either benign or malignant based on medical records.

The key difference between regression and classification is that regression predicts infinitely many possible numbers, while classification predicts a small finite set of possible categories.