Core Concepts
Unsupervised Learning
Unsupervised learning algorithms discover hidden structure in data without labeled examples. Common techniques include clustering (k-means, DBSCAN), dimensionality reduction (PCA, t-SNE), and generative modeling.
It is foundational to modern AI: the pre-training phase of large language models is essentially unsupervised, learning statistical patterns from raw internet text without human-labeled answers.
Authority Links
Related Terms
Core Concepts
Supervised Learning
Models trained on labeled data, learning to predict outcomes from inputs.
Techniques & Methods
Pre-training
Initial phase where a model learns general representations from large datasets before task-specific fine-tuning.
Model Components
Generative Model
AI model that learns to generate new data instances resembling the training distribution.
Miscellaneous
Training Data
The labeled or unlabeled dataset used to fit a model's parameters during the learning process.