Transcript PowerPoint - Sergio Pissanetzky

Structural Emergence in Partially Ordered Sets
is the Key to Intelligence
Sergio Pissanetzky
AGI-11 Conference
Overview of my research 2005 - 2011
► Initial motivation: Refactoring.
► Scope:
Refactoring is universal.
► Approach:
Computational experiments.
► Current motivation: AGI.
► Discoveries:
● Partially ordered sets as a knowledge base.
● Emergent inference.
● Emergence in complex dynamical systems.
● Indications of EI in the brain.
Computational experiments
senses and
afferent nerves
knowledge
partially
ordered set
brain
feedback
emergent
inference
feedback
natural
structures
compare
predicted
structures
The first experiment
PROGRAM
(SCRAMBLED)
a = x1 * x2
b = x3 * x4
c = x1 * x5
d = x3 * x6
e = x7 * x8
f = x7 * x2
g = x7 * x5
h = x1 * x8
i = x3 * x9
j = x9 + e
k=h+i
l =a+b
m = x4 + f
n=c +d
p = x10 + n
q = x6 + g
r = x11 + l
s = x12 + k
CANONICAL MATRIX
a
b
c
d
e
f
g
h
i
A
j
A A
k
A A
l
A
m
A A
n
A p
A
q
A
A
r
s
The result from the first experiment
REFACTORED
PROGRAM
d = x3 * x6
c = x1 * x5
n=c +d
p = x10 + n
f = x7 * x2
m = x4 + f
b = x3 * x4
a = x1 * x2
l= a+b
r = x11 + l
e = x7 * x8
j = x9 + e
i = x3 * x9
h = x1 * x8
k=h+i
s = x12 + k
g = x7 * x5
q = x6 + g
CANONICAL MATRIX (STRUCTURED)
d
c
A A n
A p
f
A m
b
a
A A
l
A r
e
A
j
i
h
A A k
A s
This process is emergent inference
g
A q
Claim
● Any dynamical system has a natural hierarchical
structure that can be found by emergent inference.
Conjectures
● Emergent inference explains emergence and
self-organization in complex dynamical systems.
● Emergent inference in the brain explains intelligence.
The representation of systems by partially ordered sets
Any system
• z = f(x, y)
Set = {x, y, z}
Partial Order = {x < z, y < z}
A computer program.
• Parser.
CFS brain model = neural network + resource preservation.
• C = connect  memory
• F = fire
 behavior
• S = shorten  intelligence, emotions, creativity
• Clustering takes place. Iteration forms clusters of clusters.
• Clusters are neural cliques, cortical columns, cortical modules.
EI is “the” key to intelligence
vs.
EI is “a” key to intelligence ?
Any “other” system can also be represented as a
partially ordered set.
Traditional AI and AGI
car position
sensors
car driving
program
car
controls
stage sensors,
actors
stage control
program
stage
controls
chess
sensors
chess playing
program
chess
controls
There is no integration, no refactoring,
and no self-programming.
The brain
car
stage
chess
drive car
senses
human
brain
manage stage
play chess
The brain integrates and refactors naturally
Emergent inference
problem
of Physics
law of Physics
raw image
image
recognition
emergent
inference
token ring
OO program
classes, objects
interdependent
tasks
parallel program
The EI system integrates and refactors naturally
Do we need a principle for intelligence?
Aeronautical Engineering.
- 1800: lift force identified as the principle of flight.
Software engineering.
- 1980’s: the automation of objects.
- 1990’s: the automation of refactoring.
Artificial intelligence.
- 2000’s: the automation of integration.
- 2010’s: the automation of self-programming.
Neuroscience.
- “the exact way in which the brain enables thought is one
of the great mysteries of science.” (Russell-Norvig).
- “we are still a long way from understanding how
cognitive processes actually work.” (Russell-Norvig) .
Emergent inference is the principle for intelligence
Final message
● EI is the principle for intelligence and AGI.