Machine Learning is gaining some useful information from the data. Usually, Machine Learning is of two types Supervised Learning and Unsupervised Learning.
Supervised Learning
Classification and Regression are examples of Machine Learning. The task of classification is to predict what class an instance of data should fall into. Another task in machine learning is a regression which predicts a numeric value. Classification deals with predicting discrete value like True/False, Male/Female, 1/2/3 Regression is used when the class to predict is of continuous value say from 0 to 100, -inf to +inf. The best example of regression is a best-fit line drawn through some data points to generalize the data points. This set of problems is called as supervised learning because here we tell the algorithm what to predict i.e. we know the label or target value.
Unsupervised Learning
In unsupervised learning, there's no label or target value given for the data. A task where similar items grouped together to form a cluster is known as clustering. Another task of unsupervised learning may be reducing the data from many features to a small number so that it becomes easier to visualize it in two or three dimensions.
The following table lists some common tasks in machine learning with algorithms used to solve these tasks.
Supervised Learning
Classification and Regression are examples of Machine Learning. The task of classification is to predict what class an instance of data should fall into. Another task in machine learning is a regression which predicts a numeric value. Classification deals with predicting discrete value like True/False, Male/Female, 1/2/3 Regression is used when the class to predict is of continuous value say from 0 to 100, -inf to +inf. The best example of regression is a best-fit line drawn through some data points to generalize the data points. This set of problems is called as supervised learning because here we tell the algorithm what to predict i.e. we know the label or target value.
Unsupervised Learning
In unsupervised learning, there's no label or target value given for the data. A task where similar items grouped together to form a cluster is known as clustering. Another task of unsupervised learning may be reducing the data from many features to a small number so that it becomes easier to visualize it in two or three dimensions.
The following table lists some common tasks in machine learning with algorithms used to solve these tasks.
| Supervise Learning tasks | |
|---|---|
| k-Nearest Neighbors | Linear |
| Naive Bayes | Locally weighted linear |
| Support Vector Machines | Ridge |
| Decision Trees | Lasso |
| Unsupervised Learning tasks | |
| k-means | Expectation minimization |
| DBSCAN | Parzen window |