Deep Learning

Embedding, explained

An embedding is a learned vector representation of an object such as a word, document, image, user, or product.

Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

An embedding is a learned vector representation of an object such as a word, document, image, user, or product.

Intuition

Embeddings turn discrete or complex things into points in a space where useful similarities become easier to compute.

Technical Definition

An embedding maps entities into a continuous vector space, usually optimized so geometric relationships reflect task-relevant semantic or statistical relationships.

Example

Search systems compare query and document embeddings to retrieve semantically related results.

Common Misunderstandings

Embedding similarity is not the same as truth.

Embedding quality depends on the training objective and data.

Same Category

More from Deep Learning

Activation FunctionAn activation function is a nonlinear operation applied inside a neural network layer.Batch NormalizationBatch normalization normalizes layer activations using batch statistics to make training more stable.ConvolutionA convolution is an operation that applies a small learned filter across local regions of data.Deep LearningDeep learning is machine learning with neural networks that learn layered representations from data.Latent SpaceLatent space is the internal representation space where a model encodes hidden factors or learned structure.Neural NetworkA neural network is a machine learning model built from layers of connected computations that transform inputs into outputs.

Essays that use this concept

Machine Learning FoundationsWhat Are Embeddings in Machine Learning? An Intuitive Guide Retrieval and RAGWhat Is Semantic Search? A Practical Explanation

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.

Browse Glossary