15
Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Embed Size (px)

Citation preview

Page 1: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Emergent Inference,or

How can a program becomea self-programming AGI system?

Sergio PissanetzkySelf-programming Workshop

AGI-11

Page 2: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Overview of Emergent Inference

► 1850 ● Helmholtz discovered Unconscious Inference.

► 2005 ● Motivation: Interest in refactoring. ● Scope: Refactoring is universal. ● Approach: Computational experiments.

► Discoveries: ● Partially ordered sets. ● Emergent inference. ● Emergence in complex dynamical systems. ● EI happens in the brain.

Page 3: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Brain experiments

knowledge

senses andafferent nerves

partiallyordered set

brainnaturalstructures

emergentinference

predictedstructures

comparefeedback

feedback

Page 4: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

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 r

A s

a = α * χb = δ * μc = α * ψd = δ * ωe = β * φf = β * χg = β * ψh = α * φi = δ * νj = ν + ek = h + il = a + bm = μ + fn = c + dp = θ + nq = ω + gr = π + ls = ρ + k

PROGRAM(SCRAMBLED)

CANONICAL MATRIX

The first experiment

Page 5: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

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

g

A q

CANONICAL MATRIX (STRUCTURED)

d = δ * ωc = α * ψn = c + dp = θ + nf = β * χm = μ + fb = δ * μa = α * χl = a + br = π + le = β * φj = ν + ei = δ * νh = α * φk = h + is = ρ + kg = β * ψq = ω + g

REFACTOREDPROGRAM

The result from the first experiment

This process is emergent inference

Page 6: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

The importance of this discovery:

● it is a rigorous mathematical solution obtained from first principles, not a phenomenological guess or an engineering compromise.● it is universal● it is a side effect of an unrelated process● it requires no domain-specific knowledge● it is not man-made● it is ready for use in computers

Page 7: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Claim

Any system has a natural hierarchical structure that can be found by emergent inference.

Emergent Inference explains emergence and self-organization in complex dynamical systems.

Emergent inference in the brain gives rise to intelligence.

Conjectures

Page 8: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Representing systems as partially ordered sets

Any system of Mathematics, Physics, Chemistry, Biology, Engineering, CS,...• Model, theory, equations.• z = f(x, y) Set = {x, y, z} Partial order = {x < z, y < z}

A computer program.• Parser.

CFS Brain model = neural network + reduce energy consumption.• C = interconnections memory• F = fire behavior• S = shrink intelligence, emotions, creativity.• Clustering takes place. Iteration forms clusters of clusters.• Clusters are neural cliques, cortical columns, cortical modules.

Page 9: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Traditional software development cycle

structure structurestructure

PROGRAM

BRAIN (human analyst)

emergentinference

emergentinference

emergentinference

• • •

• • •

stream ofexperience

knowledge

data

Page 10: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Software Categorization

Category

EmergentInference

Structuresor rules

Source ofIntelligence

Autonomy AppealKnowledgebase

Regularprogram

N frozen human some practical conventional

Narrow AI

N frozen human some futuristic conventional

Hybrid Y frozen +adaptive

human +machine

some revolutionaryconventional + posets

AGI(future)

Y adaptivemachine full singularity partiallyordered sets

Page 11: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

car position sensors

stage sensors,actors

chesssensors

Traditional AI and AGI

car drivingprogram

stage controlprogram

chess playingprogram

carcontrols

stagecontrols

chesscontrols

There is no integration, and no refactoring

Page 12: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

car

The brain

The brain integrates and refactors naturally

stage

chess

senseshumanbrain

drive car

manage stage

play chess

Page 13: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Emergent inference

problemof Physics

raw image

token ring(in C)

emergentinference

law of Physics

imagerecognition

OO programclasses, objects

interdependent tasks

parallel program

EI integrates and refactors naturally

Page 14: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

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

Page 15: Emergent Inference, or How can a program become a self-programming AGI system? Sergio Pissanetzky Self-programming Workshop AGI-11

Conclusions

● Self-programming can not be achieved without AGI.

● AGI can not be achieved by writing programs.

● EI is the principle for intelligence, AGI and self-

programming.