Drawing a comic book panel using
Human Level Artificial Intelligence
Note: To make this website free to the public
please click on an ad to support my sponsors or you
can make a tax-deductable donation using Paypal
(click on the donation icon on the left).
In this video, a
robot is given instructions to draw a comic book
panel. There are no sound in the video because I
wanted to show the viewers what the robot is thinking
while making a drawing. The flashing text and freeze
frames are the internal thoughts of the robot and not
instruction text for the viewers. These internal
thoughts describe the details of how the robot
produce intelligence.
My robot doesn't use:
planning programs/heuristic searches (used by MIT and
Stanford University), Bayesian's probability theories
for decision making, Bayesian's equation for
induction and deduction, semantic networks for
natural language understanding, predicate calculus,
common sense systems, first-order logic, rule-based
systems, genetic programming, or MACHINE LEARNING. By
the way, you can't use current AI methods to build a
robot that can draw a comic book. For example, the
IBM Watson can't be used to draw comic books. Those
researchers can spend 50 years programming
instructions into the Watson, their code foundation
disallows their robot to draw a comic book (or do
complex human tasks).
The robot extracts
intelligent pathways from memory and these
intelligent pathways form a unique computer program
inside the robot's conscious. This computer program
will provide the knowledge and procedures to
accomplish the drawing assignment. One of the most
important duties of the robot's conscious is to take
multiple images in memory to fabricate brand new
images. For example, if the robot had a front image
of a hero, but he doesn't have a back image of the
hero, then his brain will take different images from
memory to fabricate a back image of the hero. The
steps include searching memory for relevant images,
then merging these images together.
The big question is:
how exactly does the robot learn to do this? The
answer is very simple. The robot learns to cut, copy,
and paste various images together from teachers in
school. Remember when you was in Kindergarten and the
teacher taught you how to cut images and to clue
images together? That is how the robot takes various
images from memory and merges them together to form
brand new images.
This skill to
fabricate brand new images based on the robot' goals
is very important to drawing comic books. If you want
to build a robot to draw, it needs to learn things
like cutting images and gluing images together from
teachers. Cutting and gluing images is just one skill
that the robot needs. The instructions to draw a
comic book are so massive that the robot needs to
learn things in terms of a bootstrapping process
(learning knowledge through stages, from simple to
complex). The knowledge in the robots brain has to
build on itself to form complex thinking. It also
needs to understand natural language in order to
modify information in its brain. Yes, the
understanding of language is crucial to how the
robot's brain modify, organizes, and processes
information.
This video also
describes other art skills, like drawing using
perspective, generating ideas for the panel, how to
structure objects in the panel, how to balance the
composition, how to emphasize on certain characters,
and so forth.