Machine Learning - t-SNE

t-SNE (t-Distributed Stochastic Neighbor Embedding) is a dimensionality reduction algorithm commonly used for visualizing high-dimensional data in 2D or 3D. It is especially useful in machine learning and deep learning to explore data structure, such as clusters or groupings, that are not visible in high-dimensional space.

---

🔍 What t-SNE Does

t-SNE takes high-dimensional data (e.g., 100 dimensions) and maps it into a lower-dimensional space (e.g., 2D or 3D) while preserving the local structure of the data — meaning that points that are close together in high-dimensional space remain close in the lower-dimensional map.