4 5 TypesOfLearning
4 5 TypesOfLearning
Unsupervised Learning
Reinforcement Learning
Output Y
Regression
Output is continuous (real-valued).
Predicting price of a house, given its location, carpet area,
number of rooms, …
Classification
Output is discrete (integer-valued / classes / labels).
Given the weather for last 7 days, predict whether it will rain
tomorrow.
Classification
Image: https://www.toppr.com/content/story/amp/temperature-as-measure-of-hotness-or-coldness-105568/
Unsupervised Learning
Unlabeled data X.
Given a set of x’s, cluster or
summarize them.
Grouping customers
Detecting new diseases
Anomaly detection
Unsupervised Learning
Clusters
No labels
X Inputs 1,7,8, …
No feedback Input 1
Input 2 Learning Inputs 2,11,…
Find hidden Input 3
.
Algorithm
structure in data .
Input n
Inputs 9, 12, …
Image: https://towardsdatascience.com/reinforcement-learning-the-naturalist-the-hedonist-and-the-disciplined-fc335ac9289c
Reinforcement Learning
Decision process
Reward system
Learn a series of actions
Trial and error
Decision process
Reward system
Learn a series of actions
Trial and error
Performance
Agent
Environment Knowledge
Environment
Learning
Self-supervised learning
Implicit labels are extracted from data using
heuristics.
Eg Predict new video frame. Predict some missing data
based on given data set.