Solving a hard Trigonometry problem 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).
This video shows a robot
solving a hard trigonometry problem. There are no
sound in the video because I wanted to show the
viewers what the robot is thinking while solving the
problem. 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.
In the video, the robot
is given a trigonometry problem. Upon reading the
problem, the robot identify this math equation as
belonging to trigonometry. Next, knowledge about
trigonometry and algebra pours into the robot's mind
(primarily 5 containers). The reason that algebra
knowledge was also extracted is because trigonometry
uses algebra. Thus, both subject matters are
interconnected.
During the video, the
robot is writing important things down on scratch
paper. His internal mind is giving him important
facts, rules, and analytical skills. When solving
math equations, it's very important to read the
instructions in segments and to use common sense to
interpret the real meaning behind the instructions.
First, the robot interprets the math equation and
finds out what the question is. Then, the robot
looks at facts that are given in the instructions.
Next, he writes things down, uses his mind to analyze
certain aspects of the equation, and do linear steps
that teachers have taught him to solve math
equations.
For example, in the
video the robot was told the 2 triangles were
equilateral. Facts start to activate in the robot's
mind, such as: each side of a equilateral triangle
are equal. Or a triangle has 3 sides. These facts
are not given to the robot. The robot has learned
these facts in school and his mind is extracting
these facts because they are related to the math
problem. Also, a large part of the intelligence
needed to solve this problem is based on analytical
skills. These skills are also taught by teachers in
school. In the video, the robot is using analytical
skills to discover new information and ultimately
solve the math problem.
The procedures to do
math problems is based on learned information (from
teachers and instructional books). Also, practice
doing examples is another way to learn math
procedures. As the robot do more examples, his brain
forms optimal data processing instructions in
pathways in his brain. These intelligent pathways
include things like extracting facts, generating
ideas, analyzing information, following steps, and so
forth.
After many many years
learning math (algebra, trigonometry, calculus,
discrete math, etc), the robot has intelligent
pathways to solve "any" math problem, regardless of
complexity or wither the robot learned the problem
before. He can solve new and never before seen math
equations.