(ref.doc)fcca-4

CopyCat

p 157 The Slippery Slope into the Eliza Effect
[...] the "Eliza effect" [...] could be defined as the susceptibility
of people to read far more understanding than is warranted into
strings of symbols -- especially words -- strung together by
computers.

p 167 The Dubious Claim of Cross-domain Analogy-making
[ACME, by Holyoak and Thagard, 1989] ACME deals with no domains at all
-- just strings.

p 176 On the possibility of a representation module
We are deeply skeptical [...] about the feasibility of [...] a
separation of perception from the rest of cognition.

p 177 BACON: A case study
[...] the success of the program relies almost entirely on its being
given data that have already been represented in nearly-optimal form,
using after-the-fact knowledge [...]

p 180 Models of Analogical Thought
Let us consider two analogies involving DNA. The first is and analogy
between DNA and a zipper [...] The second analogy involves comparing
DNA to the source code (i.e. non executable high-level code) of a
computer program.

p 182 Current models of analogical thought
[SME] ...the discovery of the similar structure in these
representations is not a difficult task.

p 196
Who is the First Lady of England?

p 198
By "conceptual slippage", I mean the context-induce dislodging of one
concept by a closely related one, inside the mental representation of
some situation.

p 221
Bottom-up codelets: "noticers"
Top-down codelets: "seekers"

p 232 A seeming paradox: Randomness in the service of intelligence
...this appearance of nonsensicality is an illusion caused by a
confusion of levels [top-level macro-decisions vs low-level
micro-explorations] 

Thus, randomness is used in the service of, and not in opposition to,
intelligent nonrandom choice.

Fluidity is an emergent quality, and to simulate it accurately
requires an underlying randomness.

p 256 
[    a b c    -> a b d
  m r r j j j ->   ?
]
Arriving at the deeper answer of mrrjjjj requires not only the
insights brought about by the strong pressures in the problem, but
also a large degree of patience and persistence in the face of
uncertainty.

p 307 Prolegomena to Any Future Metacat
Computer models often study the static properties of concepts --
context-independent judgements of membership in categories, for
instance -- but the question of how concepts stretch and bend and
adapt themselves to unanticipated situations is virtually never
addressed.

p 308
...the entirety of [Copycat's] processing can be called high-level
perception [...] The ability to reperceive, in short, is at the crux
of creativity.