A type of machine learning where the model is trained on input data without explicit supervision or labeled outputs. The goal is to discover patterns, relationships, or structures in the data without the need for pre-labeled responses.
Unsupervised learning
- Clustering group similar data points together based on certain characteristics or features, without prior knowledge of the groups
- Anomaly detection identify groups or patterns in the data, anomaly detection focuses on identifying data points that are significantly different from the majority of the data. These data points are often referred to as anomalies, outliers, or novelties.
Recommender Systems
- Collaborative filtering predict the preferences or ratings of users for items (such as movies, books, products) based on the preferences or ratings of similar users.
- Recommender systems implementation detail Implementing a recommender system involves several key steps and considerations.
- Content-based filtering generate recommendations based on the features or characteristics of items themselves, rather than relying on the preferences of other users. It is a form of unsupervised learning where the system learns to recommend items to users by understanding the content or attributes of the items and matching them with user preferences.
- Principal Component Analysis a dimensionality reduction technique commonly used in unsupervised learning and data analysis. Its main objective is to simplify the complexity of high-dimensional data while preserving the essential structure or patterns within it. PCA achieves this by transforming the original variables into a new set of orthogonal variables called principal components.
Reinforcement learning
- What is Reinforcement Learning? an agent learns to make decisions by interacting with an environment. The agent learns to achieve a goal or maximize a reward by taking actions in the environment and observing the outcomes of those actions.
- Self-action value function
- Continuous state spaces