Semantics can emerge from programs that learn
A system with sufficiently complex learning mechanisms can possess semantics if it meets a principle of inductive adequacy: ie the system should possess inductive mechanisms capable of producing all the knowledge constructs it uses in its behaviour.
For example, a rule-based system must be able to generate new rules, a frame-based a system must be able to generate new frames, and so forth.

Paul Thagard, 1986.
CONTEXT(Help)
-
Artificial Intelligence »Artificial Intelligence
▲
Can computers think? [1] »Can computers think? [1]
▲
Yes: physical symbol systems can think [3] »Yes: physical symbol systems can think [3]
▲
The Chinese Room Argument [4] »The Chinese Room Argument [4]
▲
The Syntax-Semantics Barrier »The Syntax-Semantics Barrier
▲
Programs that learn can overcome the barrier »Programs that learn can overcome the barrier
■
Semantics can emerge from programs that learn
+Comments (0)
+Citations (0)
+About