/
← L3: Supervised Learning L5: Reinforcement Learning →
Module 2: ML Foundation

L4: Unsupervised Learning

L4: Unsupervised Learning

20:00

Unsupervised learning is a type of machine learning where the algorithm is trained on data that has no labeled outputs. In other words, the algorithm is given input data without explicit instructions on what to do with it. The goal of unsupervised learning is to find patterns, structures, or relationships within the data.

Since there are no labels or correct answers provided, unsupervised learning algorithms try to identify underlying structures by themselves, typically by grouping similar data points or reducing the dimensionality of the data.

Key types of unsupervised learning:

  1. Clustering : This involves grouping similar data points together based on certain features. The algorithm discovers the inherent structure in the data. Examples include:

    • K-means clustering : Groups data points into a predefined number of clusters.

    • Hierarchical clustering : Builds a tree-like structure of clusters.

    • DBSCAN (Density-Based Spatial Clustering of Applications with Noise) : Identifies clusters based on the density of data points.

  2. Dimensionality Reduction : This technique reduces the number of features or variables in the data while retaining important information. It's often used for simplifying data or for visualization. Examples include:

    • Principal Component Analysis (PCA) : Reduces data to its most important dimensions.

    • t-Distributed Stochastic Neighbor Embedding (t-SNE) : A technique used for visualizing high-dimensional data.

Applications of unsupervised learning:

  • Market segmentation : Grouping customers with similar behavior for targeted marketing.

  • Anomaly detection : Identifying unusual patterns, such as detecting fraud or network intrusions.

  • Recommendation systems : Recommending products based on patterns in customer behavior.

  • Image compression : Reducing the size of images by identifying important features.

Unsupervised learning is widely used when we don't have labeled data or when the goal is to discover hidden structures in data, such as customer segmentation or anomaly detection.