abstract representation
A lower-dimensional, simplified encoding of high-dimensional input data that captures the most relevant and predictable information while discarding noise and irrelevant details
As defined in Yann LeCun: Special Lecture on AI and World Models
Where it comes up · 1
Most important claims · 3 of 3Search all claims for “abstract representation” →
- Abstract representations are fundamental not just for building intelligent AI systems but for all of science: in physics, chemistry, and biology, scientists always identify abstractions (particles, atoms, molecules, organisms) that allow tractable modeling and prediction without simulating underlying details like quantum mechanics.Yann LeCun: Special Lecture on AI and World Models
- JEPA (joint embedding predictive architecture) is an architecture that predicts abstract representations of future states rather than reconstructing raw sensory details, eliminating the need to predict unpredictable information by focusing only on predictable, relevant information.Yann LeCun: Special Lecture on AI and World Models
- Complex systems like turbojet engines, chemical plants, oil refineries, and patients with chronic conditions are too complex to model with reductionist equations but can be modeled phenomenologically using trained world models with abstract representations.Yann LeCun: Special Lecture on AI and World Models