Generalization
A model's ability to perform well on new, unseen cases — not just the examples it was trained on.
At a glance
Key signals
0% cross fields · reaches 10 more
- Machine Learning
- Statistics
- Cognitive Science
- Explanation
- Examples
- Misconception
- Sourced relations
- Attribution
Dependencies
What this concept builds on and what it makes possible — derived from the atlas’s dependency, causal and structural relations, not from every related edge.
Foundations · builds on
Machine learningenablesGeneralizationEstablished
Learning succeeds when the model generalises beyond its examples.
Mechanism: A model that only repeats its training examples has not learned; usable learning shows up as the capacity to generalise.
Supervised learningenablesGeneralizationEstablished
supervised learning enables Generalization.
Mechanism: Supervised learning aims at generalization: a good model captures the true pattern, so it performs well on data it never trained on.
- Wikipedia (English & German editions) verifiedmoderate evidence
Enables · leads to
GeneralizationenablesPredictionEstablished
Generalisation is what lets a model predict unseen cases.
Mechanism: A model can only make a useful prediction about a new case because it generalised the pattern from the cases it saw.
Structural role & consequence
Interpreted from the current atlas graph — what the connections mean, not just how many there are.
Directly enables 1 concept; following enables/causes relations, 1 concept is downstream across 3 disciplines.
structural · Follows only enables/causes dependency edges — not general relatedness.
Currently dark in the atlas: no key date stored · 5 of 5 of its relations lack claim-level evidence.
atlas representation · Describes the current Thinking OS representation, not the state of the world.
Builds on 2 foundations (requires / depends-on / derived-from / emerges-from).
structural · Structural graph analysis — not a claim of importance, causation or history.
Structural neighbourhood: 5 → 35 → 155 concepts reachable within 3 hops.
structural · Structural reach — being reachable is not the same as being understood.
cross-field
5 within-field, 0 cross-field
Strengths & constraints
Constraints
- Evidence coverage currently thin in the atlas — few of its relationships carry claim-level evidence. atlas representation
- No dated history stored — the atlas records no key date for this concept. atlas representation
Conditions
- Its dependency reading rests on 2 foundation relations. structural
- Read structurally — most of its relationships carry no external evidence yet, so claims here are graph-derived. structural
Dependency radial
What this concept builds on (left) and what it makes possible (right) — derived from dependency and causal relations.
Seen through each discipline
How this concept sits in each of its fields — derived from its real connections in the graph, not asserted.
Through this lens it connects to Machine learning, Supervised learning and Overfitting.
Through this lens it connects to Machine learning, Overfitting and Prediction.
Through this lens it connects to Analogy.
Check yourself
A quick check against a common misconception. Nothing is scored — picking the tempting-but-wrong answer just flags an idea worth revisiting.
Which statement is correct?
If a model is perfect on its training examples, it has learned well.
Perfect on training but poor on new cases means it memorised rather than learned — that is overfitting.
Look for: Learner judges a model only by its training accuracy and expects it to work equally well on new cases.
Where you'll meet it
Journeys that walk you through this idea. You may recognise it from more than one.
Related ideas to explore
Concepts that look related but are not yet connected here — candidates for a connection to reason about, not established links.
This idea also appears in…
The same structure shows up in other disciplines. These are real recurrences drawn from the graph — a starting point for asking “what carries over, and what changes?”
Probability24 disciplines · 21 concepts
Concepts
shares a mental model
shares a mental model
explicitly analogous
shares a mental model
shares a mental model
shares a mental model
The point of learning is not to memorise the examples — it is to handle new ones. A model that generalises has captured the underlying pattern, not the exact answers. This is exactly what YOU do when you carry an idea into a new subject.
Mental models at work here
- Connects 5 other ideas across 3 disciplines.
- A cross-disciplinary bridge — its connections reach into 10 other fields.
- Most of its connections are of the “Cause & effect” kind.
- It exercises 1 reusable thinking pattern.
- It features in 1 learning journey.
Derived from the graph’s real structure — observations, not a score.
Sources
- Categorizing numeric information for generalization (1985) verified
- Generalization from natural language text (1983) verified
- Generalization (2005) verified
- Empirical Generalization (2005) verified