value-centric abstraction
A form of abstraction that operates on continuous domains by comparing instances via continuous distance functions to create prototypes, grounded in geometry; similar to human perception and intuition.
As defined in Francois Chollet | Why abstraction is the key to intelligence, and what we’re still missing
Where it comes up · 1
Most important claims · 1 of 1Search all claims for “value-centric abstraction” →
- Deep learning excels at value-centric abstraction and is fundamentally a geometrical method performing smooth geometric morphing between input and target vector spaces via gradient descent, learning a distance function that defines a manifold; it is therefore well-suited to perception problems but cannot solve discrete problems requiring program-centric abstraction.Francois Chollet | Why abstraction is the key to intelligence, and what we’re still missing