AI engineering glossary · ML fundamentals
What is manifold hypothesis?
Manifold hypothesis: The idea that real high-dimensional data such as images actually lies close to a much lower-dimensional curved surface within the full space. It explains why learning is possible despite huge feature counts and motivates methods that discover compact representations.
Manifold hypothesis: an example
Images of a rotating object have millions of pixels, yet only a few numbers, such as angle and lighting, describe the variation.
Related terms
More ML fundamentals terms
- Meta-learning
- Model
- Model capacity
- Model selection
- Model variance
- Nested cross-validation
- No free lunch theorem
- Noise
Where you learn it
Manifold hypothesis is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.