Welcome to the Machine Learning Course for Black and Indigenous Students!

This program is offered by Vector Institute in its drive to build research and expand career pathways in the field of AI for under-represented populations.

Instructor: Bonaventure Molokwu | Tutorial Developer: Manmeet Kaur Baxi | Course Tutors: Yinka Oladimeji and Manmeet Kaur Baxi | Course Director: Shingai Manjengwa (@Tjido)

Never stop learning!

Classification

• A process of categorizing a given set of data into classes, it can be performed on both structured and unstructured data.
• Includes predicting the class of given data points. (classes → targets, labels, categories)
• The task of approximating the mapping function from input variables to discrete output variables.
• The main goal is to identify which class/category the new data will fall into.
• Classification, in short, is a form of “pattern recognition”

Examples:

• Heart disease detection (has heart disease/ does not have heart disease)
• Filtering emails into “spam” or “not spam”.
• Classify recent user behaviour as churn or not.

Types of Classification Algorithms:

1. Binary Classification

• A type of classification with two outcomes, for e.g. – either true or false.

• Some popular algorithms:

  1. Logistic Regression (Specifically for binary classification & natively don’t support more than two types of classes)
  2. k-Nearest Neighbours (KNN)
  3. Decision Trees
  4. Support Vector Machines (SVM) (Specifically for binary classification & natively don’t support more than two types of classes)
  5. Naive Bayes

• Examples: Email spam detection, User churn prediction, Cancer detection

  

2. Multi-class Classification