Which type of learning involves identifying patterns without labeled training data?

Unsupervised learning is a type of machine learning where the model is trained on data that does not have labeled responses or outcomes associated with it. In this context, the key characteristic of unsupervised learning is that it seeks to identify hidden patterns or intrinsic structures within the input data.

For example, in unsupervised learning, algorithms might group data points into clusters based on their features or identify outliers without prior knowledge of what those clusters or outliers represent. Common techniques in unsupervised learning include clustering algorithms such as K-means and dimensionality reduction techniques like Principal Component Analysis (PCA).

This contrasts with other types of learning: supervised learning relies on labeled data to make predictions, reinforcement learning learns from interactions within an environment through rewards and penalties, and deep learning is a subfield that utilizes neural networks, often in both supervised and unsupervised contexts but typically on large datasets that can be either labeled or not. Each of these approaches has distinct use cases and methodologies that set them apart from unsupervised learning.