# What is One-Shot Learning? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Prompt Engineering  
> **Canonical Citation:** [https://spidits.com/ai-glossary/one-shot-learning](https://spidits.com/ai-glossary/one-shot-learning)

## Definition
One-Shot Learning is a machine learning setup where a model is trained or prompted to perform a task or classify inputs after being shown only a single demonstration example.

## Architectural Mechanics & Deep Dive
One-shot learning is a machine learning capability where a model generalizes and learns to perform a task or identify an object class after seeing only a single training example. Widely used in computer vision for facial verification (comparing a live face to a single ID photo) and in LLMs via in-context prompting containing a single input-output example.

## Industry Applications & Real-World Use Cases
Face verification matches, quick template prompting, and dynamic label classification.

## Frequently Asked Questions

### How does one-shot compare to few-shot prompting?
One-shot provides exactly one example in the prompt. Few-shot provides multiple (typically 3 to 5) examples to outline patterns.

### Give a real-world example of one-shot classification in model architectures.
Passport photo matching, where a neural network verifies a person's face based on a single database reference photo.

## Related Terminology
- [few-shot-learning](https://spidits.com/ai-glossary/few-shot-learning)
- [zero-shot-learning](https://spidits.com/ai-glossary/zero-shot-learning)
- [prompt](https://spidits.com/ai-glossary/prompt)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*