Below are examples of both supervised and unsupervised learning algorithms and tasks.

Supervised Learning

In supervised learning, the model is trained on a labeled dataset, which means that each training example is paired with an output label.

Examples of Supervised Learning Algorithms:

1. Linear Regression: Predicting a continuous value, like house prices based on features like the number of bedrooms, bathrooms, etc.
2. Logistic Regression: Used for classification problems, such as email spam detection (labeling emails as spam or not spam).
3. Support Vector Machines: Classification of data into different classes, such as recognizing handwritten digits.
4. Decision Trees and Random Forests: Used for tasks like classifying a fruit as an apple or orange based on features like color and size.
5. Neural Networks: Deep learning models that can be used for complex tasks like image recognition, speech recognition, etc.

Unsupervised Learning

Unsupervised learning algorithms work with datasets that have no labels. They are used to draw inferences and find patterns from the input data.

Examples of Unsupervised Learning Algorithms:

1. K-Means Clustering: Grouping customers into different segments based on their purchasing behavior.
2. Hierarchical Clustering: Used to build a hierarchy of clusters, such as categorizing documents into topics.
3. Principal Component Analysis (PCA): Reducing the dimensionality of data while preserving as much variability as possible.
4. Autoencoders: A type of neural network used to encode the input into a lower-dimensional form and then reconstruct the original input.
5. Gaussian Mixture Models (GMM): Used to model and categorize data that is assumed to be generated from several different underlying Gaussian distributions.

These examples cover a wide range of practical applications in various fields like finance, marketing, healthcare, and more. The supervised learning algorithms rely on labeled data to predict or classify unknown inputs, while the unsupervised learning algorithms discover hidden patterns and relationships in unlabeled data.