Few-shot learning is a machine learning paradigm where a model acquires the ability to perform a new task from K exemplars (typically K ∈ {1, 5, 10, 32}), by transferring structural knowledge acquired from a distribution of related source tasks. Parameters: K = support set size, N = number of classes in the support set, query set size Q, task distribution p(T) over source tasks, and the embedding function h_θ that maps inputs to a representation space where similarity-based classification generalizes to novel tasks. Persistence mechanism: encoded as trainable network weights and fine-tuned meta-objectives stored in model checkpoints; taught as a formal methodology through research literature, benchmarks (e.g., Omniglot, CIFAR-FS, FC100), and open-source implementations. [formal: paucitas | substrate: mind | horizon: a life | explicit: yes | epoch: 0.08]
Accepted ontology entry
few-shot-learning
Few-shot learning is a machine learning paradigm where a model acquires the ability to perform a new task from K exemplars (typically K ∈ {1, 5, 10, 32}), by transferring structural knowledge acquired from a distribution of related source…
Definition
Why it is in scope
few-shot-learning is a human-made machine learning approach where a model learns to perform a task from only a small number of training examples, typically by leveraging prior knowledge from related tasks or meta-learning objectives
Names and aliases
- few-shot-learningen · CANONICAL
Relations from this entry
- cmrg0scos00ef2a1nklfvbk7xINSTANCE_OF →
few-shot-learning is a specific kind of machine learning where models learn from very limited examples. A competent speaker would call it a type of machine learning. The nearest kind ladder is direct — no intermediate rung between few-shot-learning and machine learning.
- cmsdcks2103r73vv3v8qlmtjiDERIVED_FROM →
Few-shot learning is a sub-paradigm within supervised learning where classification or regression operates with very few labeled examples per class. Supervised learning (the broader paradigm of learning from labeled data) existed first and conceptually enabled few-shot learning as a specialization addressing data-scarce scenarios. Direction: supervised learning → few-shot-learning.
- cmsnkxr8304931q13h9aripcxINSTANCE_OF →
Few-shot learning is a specific kind of in-context learning — it uses a small number of examples within the context window to learn a new task. A competent speaker calls few-shot learning a type of in-context learning. Nearest kind check: few-shot learning IS a form of in-context learning.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 9, 2026, 9:00 PM UTC
- Content hash
- e8e7b1895dc8158e2e21b01485b353772591ae77f3465ed248ec610ab4fc2ffa