Tasks: going from inputs (stimuli) to outputs
(responses)
The most primitive solution: a lookup table which specifies an
output for every input
The problem with lookup tables:
There may be too many inputs to store (the world is continuous, after all).
There is a need for the system to be able to respond appropriately
to novel inputs.
The alternative solution: a function from inputs to outputs
AI is about these functions: what they might look like for
tasks requiring "intelligence".
The functions may be very complex, requiring one or more transformations
of the input, internal representations.
Are they explicit (directly interpretable),
or are they in a form that looks like garbage to an outside
observer (even though they serve their function for the system)?
Are they localized (in one place), or are they
distributed throughout the system?
Are they propositional (language-like), or
are they in some other form, for example, more like images?
Are they static or dynamic? Do they just sit there
or do they "happen"?
Are there different kinds of representations for different
domains that have little in common with each other?
Wholes consisting of parts, which are in turn wholes consisting
of parts: recursivestructure
Slots (roles) and fillers (values)
In an object, the COLOR slot may have filler GREEN
and the FUNCTION slot may have filler CONTAINING_FOOD.
In an event, the AGENT slot may have filler TYLER and
the INSTRUMENT slot may have filler SCISSORS3.
Truth and falsehood
Generality (abstraction)
The generalization (concept) TURNIP is an abstraction over
all turnips, including, for example, TURNIP4.
The generalization (concept) BORROW is an abstraction over
all instances of borrowing, including, for example, BORROW8, in which
Shelby borrowed a pair of scissors from Tyler.