http://cogprints.org/1595/
Grounding Symbolic Capacity in Robotic Capacity
Depite considerations in favor of symbol grounding, neither pure
connectionism nor pure nonsymbolic robotics can be counted out yet, in
the path to robotic Turing Test. So far only computationalism and pure
AI have fallen by the wayside. If it turns out that no internal symbols
at all underlie our symbolic (email Turing Test) capacity, if dynamic
states of neural nets alone or sensorimotor mechanisms subserving
robotic capacities alone can successfully generate our full robotic
performance capacity without symbols, that is still the decisive test
for the presence of mind and everyone should be ready to accept the
verdict. For even if we should happen to be wrong about such a robot,
it is clear that no one (not even an advocate of the stronger
neural-equivalence version of the Turing Test, nor even the Blind
Watchmaker who designed us but isno more a mind-reader than we are) can
ever hope to be the wiser.
Harnad, Stevan
Cognitive Psychology
Robotics
Stevan
Harnad