AI Glossary Term

What is ANN (Approximate Nearest Neighbor)?

Definition

Algorithms that find vectors close to a query without exhaustive comparison, trading exactness for speed.

Related terms

HNSW
A graph-based index structure for fast approximate nearest-neighbor search over high-dimensional vectors.
RoPE (Rotary Positional Embeddings)
A positional encoding method that rotates query and key vectors to encode relative token positions.
Continual Learning
Training approaches that let a model keep learning from new data without forgetting prior knowledge.
Intent Classification
Predicting the user's purpose from a text query to route it correctly.
Retrieval
Finding relevant documents or records from a knowledge source for a query.
Unsupervised Learning
Learning patterns from unlabeled data without explicit target outputs.

Learn more in our free guides

Warmup and Cosine Annealing SchedulesK-Nearest NeighborsAI in Inventory Demand PlanningAI in Urban Planning and Smart Cities
Browse the full AI GlossaryExplore all free AI guides