(you
may click the subfile number to be viewed, or scroll down)
This
file contains the following subfiles:
1 - other tasks
2 - status of this project
3 - series of experiments
(subfile
1: targeted non-linguistic
tasks)
The attempt at representation is being manifested in a computer program
that is intended 1) to learn to converse in a way comprehensible to
native speakers of whichever language is used, and 2) to use a
programming structure functionally identical to one already shown to be
appropriate for biological and economic simulations, experiments with
cellular automata, musical composition, locomotion/navigation,
character recognition, and playing some games.
(subfile 2:
status of the project)
I have tried to use tenses very carefully in this text: present
indicative means “code exists and runs”; simple future means “I am
certain that I know exactly how to write the code, but haven’t done so
yet”; and any type of conditional or subjunctive means “I haven't
decided how this can be coded” or “I have, as yet, no code for
this module in mind.” However, as I said, the status is
changing daily as code
is written. I estimate the code completed to be about 15% of that
required.
(subfile 3:
earlier experiments)
In retrospect, the earlier programs are understood to have been
preparatory exercises for the current project; they are described
in part two of this paper. They provided experience with a number of
areas crucial to the current algorithm, including learning by
observation, content-addressable memory, large feature spaces, natural
selection as learning, and originality vs. plagiarism.