Achieving Advanced Machine Consciousness via Artificial General Intelligence in Virtual Worlds

1

Achieving Advanced Machine Consciousness via
Artificial General Intelligence in Virtual Worlds
Ben Goertzel, PhD
2

Contents

• The Nature of Consciousness
• Artificial General Intelligence versus Narrow AI
• The Novamente and OpenCog AGI Projects
• The Marriage of AGI and Virtual Worlds
• Initial Application Virtual Pet Brain

3

• A Useful Philosophical Perspective
• On Consciousness
• In

4
(No Transcript)
5

Metaphysical Foundation Peircean/Jungian
Categories
First raw, unprocessed being e.g.
qualia Second reaction e.g. pure physical
reaction Third relationship (beyond Peirce
Fourth synergy, etc.)
6

Archetypal Perspectives
First person firstness of X the world as
directly experienced the stream of qualia
Third person thirdness of X the world as an
objective relational structure, a network of
patterns Fourth person (normally called second
person) fourthness of X the synergy of
relationships the Buber-ian I-You The real
second person secondness of X experiencing the
world as an automaton?
7

Inter-perspective correlations
Example of a hypothesis spanning
perspectives The more intense qualia
experienced by a system, correspond to the more
informationally significant patterns detectable
in that system by an intelligent, well-informed
observer
8

Reflective consciousness and other emergent
constructs

• Hypothesis
• Among the more informationally significant
  patterns in generally intelligent systems are
• The phenomenal self
• Reflective consciousness
• The illusion of will

9

Modeling Reflective Consciousness, Self and Will
Using Hypersets
Hypothesis The qualia we humans describe as
reflective awareness, self and will
correspond to patterns in our brains that are
conveniently expressible in terms of hypersets
(non-well-founded sets)
10

Modeling Reflective Consciousness, Self and
Will Using Hypersets
S is conscious of X" is defined as The
declarative content that "S is conscious of X"
correlates with "X is a pattern in S", where S
is an intelligent systems phenomenal self "S
wills X" is defined as The declarative content
that "S wills X" causally implies "S does X,
where S is an intelligent systems phenomenal
self "X is part of S's self" is defined as The
declarative content that "X is a part of S's
self" correlates with "X is a persistent pattern
in S over time"
11

Evaluating Hypersets as Patterns in Dynamical
Systems
The hyperset defined by X F(X) may be evaluated
as a pattern in a system by comparing the
iterates A F(A) F(F(A)) to the systems
trajectory at various times for various A
12

Summary

• There are multiple archetypal perspectives
  First, Second, Third, Fourth person,
• There are correlations between the different
  perspectives (e.g. intense qualia correspond to
  informational patterns)
• There are specific emergent structures (self,
  will, reflection) that correlate with intense
  patterns/qualia in generally intelligent systems
• It may be interesting to model these emergent
  structures using hypersets

13

• Artificial General Intelligence
• versus Narrow AI
• In

14

Artificial General Intelligence (AGI)

• The ability to achieve complex goals in complex
  environments using limited computational
  resources
• Autonomy
• Practical understanding of self and others
• Understanding what the problem is as opposed
  to just solving problems posed explicitly by
  programmers
• Solving problems that were not known to the
  programmers

15

Narrow AI

• The vast majority of AI research practiced in
  academia and industry today fits into the Narrow
  AI category
• Each Narrow AI program is (in the ideal case)
  highly competent at carrying out certain complex
  goals in certain environments
• Chess-playing, medical diagnosis, car-driving,
  etc.

16
Today, Narrow AI Dominates the AI Field (in both
academia and applications)
Deep Blue - whoops us pesky humans at chess - but
cant learn to play a new game based on a
description of the game rules DARPA Grand
Challenge - a great leap forward -- but it cant
learn to drive different types of vehicles
besides cars (trucks, boats, motorcycles) Google
- fantastic service but cant answer complex
questions. Whatever happened to AskJeeves?
17
2001
18
(No Transcript)
19

Artificial General Intelligence (AGI)

• Hypothesis Human-level general intelligence
  naturally comes along with the emergence of
• Phenomenal self
• Reflective consciousness
• Illusion of free will

20

• A Pragmatic, Integrative
• Approach to Advanced AGI
• In

21

Novamente Cognition Engine
The Novamente Cognition Engine (NCE) represents a
serious scientific/engineering effort to create
powerful artificial general intelligence, via an
integrative, computer science based
approach While the NCE may be applied in many
different domains, the most natural way to
develop and apply it, at the current stage, is in
the context of controlling physically and/or
virtually embodied intelligent agents For more
detail on the NCE, see novamente.net/papers
22

Open Cognition Framework
The OpenCog project (opencog.org) is an
open-source offshoot of the Novamente project,
which has been seeded in 2008 with significant
AGI code donated by Novamente LLC It includes
the RelEx NL comprehension system, founded on the
CMU link parser plus additional rule-based and
statistical NLP methods
23

• The essential dynamics of these AGI systems
  follows the basic logic of animal behavior
• Enact a procedure so that
• Context Procedure gt Goals
• i.e.
• at each moment, based on its observations and
  memories, the system chooses to enact procedures
  that it estimates (based on the properties of the
  current context) will enable it to achieve its
  goals, over the time-scales these goals refer to

24

• There is an important distinction between
  explicit goals and implicit goals
• Explicit goals the objective-functions the
  system explicitly chooses actions in order to
  maximize
• Implicit goals the objective-functions the
  system actually does habitually maximize, in
  practice
• For a system that is both rational, and capable
  with respect to its goals in its environment,
  these will be basically the same. But in many
  real cases, they may be radically different

25
Goal Dynamics

• A sufficiently intelligent system is continually
  creating new subgoals of its current goals
• Some intelligent systems may be able to replace
  their top-level supergoals with new ones, based
  on various dynamics
• Goals may operate on radically different
  time-scales
• Humans habitually experience subgoal alienation
  -- what was once a subgoal of some other goal,
  becomes a top-level goal in itself. AIs need
  not be so prone to this phenomenon

26

Five key aspects of AGI design

• Knowledge Representation
• Cognitive Architecture
• Knowledge Creation
• Environment / Education (incl. physical virtual
  robotics)
• Emergent Structures and Dynamics

There is no single, mechanism-level magic trick
at the heart of general intelligence rather,
intelligence arises in appropriately-constructed
complex systems as an emergent phenomenon. The
trick is to figure out what sorts of complex
systems will give rise to general intelligence as
an emergent property. There is unlikely to be
one correct answer to this question but all
we need to build the first thinking machine is
one of the many correct answers.
27
The Novamente/OpenCog high-level cognitive
architecture is based on the state of the art in
cognitive psychology and cognitive neuroscience.
Most cognitive functions are distributed across
the whole system, yet principally guided by some
particular module.
28

Unique hypergraph knowledge representation
bridges the gap between subsymbolic (neural net)
and symbolic (logic / semantic net)
representations, achieving the advantages of
both, and synergies resulting from their
combination.
29
Each cognitive processing machine, within each
unit, contains an Atom Space full of nodes and
links representing knowledge, plus a set of
cognitive processes acting on this Atom Space,
encapsulated in software objects called
MindAgents and scheduled by a Scheduler object.
30
Each box in the cognitive architecture diagram,
corresponds at the software level to a cluster of
machines called a unit, containing a local
persistent DB plus one or more cognitive
processing machines.
31
Algorithms for Procedural and Declarative
Knowledge Creation
Probabilistic Logic Networks (for gaining
declarative knowledge directly) The first
general, practical integration of probability
theory and symbolic logic. Extremely broad
applicability. Successful track record in bio
text mining, virtual agent control. Based on
mathematics described in Probabilistic Logic
Networks, published by Springer in 2008
MOSES Probabilistic Evolutionary Learning (for
gaining procedural knowledge directly) Combines
the power of two leading AI paradigms
evolutionary and probabilistic learning Extremely
broad applicability. Successful track record in
bioinformatics, text and data mining, and virtual
agent control.
32
Economic Attention Allocation
Each node or link in the knowledge network is
tagged with a probabilistic truth value, and also
with an attention value, containing Short-Term
Importance and Long-Term Importance
components. An artificial-economics-based process
is used to update these attention values
dynamically -- a complex, adaptive nonlinear
process.
33
The system contains multiple heuristics for Atom
creation, including blending of existing Atoms
34
Atoms associated in a dynamic map may be
grouped to form new Atoms the Atomspace hence
explicitly representing patterns in itself
35
Hypothesis Integrative Design Can Allow
Multiple AI Algorithms to Quell Each Others
Combinatorial Explosions
Pattern Mining
Probabilistic Evolutionary Program Learning
Probabilistic Logical Inference
Economic Attention Allocation
36

Overall Philosophy
Algorithms for declarative and procedural
knowledge creation and attention allocation
integrated with appropriate synergy and acting
on an appropriately powerful knoweldge
representation used to control a system
pursuing complex goals may lead to the
emergence of system structures characteristic of
general intelligence
37
Why Do I Believe I Can Succeed When So Many
Others Have Failed?

• Approach is based on a well-reasoned,
  comprehensive theory of mind, which dictates a
  unified approach to the five key aspects
  mentioned above
• Knowledge representation
• Learning/reasoning
• Cognitive architecture
• Embodiment / interaction
• Emergent structures / dynamics
• Cognitive Theory summarized in The Hidden Pattern
  (Ben Goertzel, Brown Walker Press, 2006)
• The specific algorithms and data structures
  chosen to implement this theory of mind are
  efficient, robust and scalable and, so is the
  software implementation

38

• The Marriage of AGI
• and Virtual Worlds
• In

39
How Important Is Embodiment?

• Some AI theorists believe that robotic embodiment
  is necessary for the achievement of powerful AGI
• Others believe embodiment is entirely unnecessary
• We believe embodiment is extremely convenient for
  AGI though perhaps not strictly necessary and
  that virtual-world embodiment is an important,
  pragmatic and scalable approach to pursue
  alongside physical-robot embodiment

40

• Public virtual worlds provide a wonderful
  opportunity for teaching baby AIs not only the
  experience of embodiment, but the massive plus of
  having hundreds of thousands or millions of
  teachers helping the AI to learn

41
Current virtual world platforms have some fairly
severe limitations, which fortunately are fairly
easily remedied
Agent control relies on animations and other
simplified mechanisms, rather than having virtual
servomotors associated with each joint of an
agents skeleton
Object-object interactions are oversimplified,
making tool use difficult
42
Example solution Integration of a robot
simulator with a virtual world engine

Player / Gazebo 3D robot control simulation
framework
RealXTend/OpenSim open-source virtual world
It seems feasible to replace OpenSims physics
engine with appropriate components of
Player/Gazebo, and make coordinated OpenSim
client modifications
43
Cognitive Control of agents in current virtual
worlds -- e.g. Second Life, Multiverse, HiPiHi
e.g. take one step forward
non-parametrized behavior signals
Cognition Engine
high-level perceptual data
Coordinates of objects, Labeled with type
44
Hybrid Generally-Intelligent Robot Brain
Architecture, version 1
e.g. Force F exerted by servomotor M in
direction D
e.g. take one step forward, using gait parameter
vector V
Behavioral postprocessor
action signals
behavior signals
Behavioral modules
Cognition Engine
Neural net module evolver
Object classification modules
raw perceptions
Perceptual preprocessor
mid-level perceptual data
e.g. video output of camera eyes
e.g. 3D polygonal mesh, marked up with limited
object Identification information
45
(No Transcript)
46
(No Transcript)
47
(No Transcript)
48

• Application
• Novamente Pet Brain
• In

49
Novamente Pet Brain
The Pet Brain utilizes a specialized version of
the Novamente Cognition Engine to provide
unprecedentedly intelligent virtual pets with
individual personalities, and the ability to
learn spontaneously and through training. Pets
understand simple English and future versions to
include language generation
The Pet Brain incorporates MOSES learning to
allow pets to learn tricks, and Probabilistic
Logic Networks (PLN) inference regulates
emotion-behavior interactions, and allows
generalization based on experience.
50
Demo Screenshots Training
Novamente-powered smart pets can be taught to do
simple or complex tricks - from sitting to
playing soccer or learning a dance - by learning
from a combination of encouragement,
reinforcement and demonstration.
Reinforce
Imitate
Teach
Correct
give sit command
reinforce and/or correct.
show example
successful sit, great
51
Teaching with a Partner
In partner-based teaching, the pet understands
that one avatar is the teacher and the other is
the student, whose interactions with the teacher
the pet is supposed to understand, abstract, and
imitate
52
Next Step Language Learning
Our initial virtual pets have robust but
simplistic language understanding, sufficient to
learn an unlimited variety of commands In the
next version, integration of Novamentes RelEx
language processing system with the Novamente Pet
Brain will provide a more powerful approach to
embodied language learning With human-controlled
avatars as language teachers, Novamente-controlled
virtual agents will be able to rapidly improve
their language comprehension and generation via
adaptive learning
53
Next-Gen Pet/Baby Brain Architecture
The next generation of the Avatar Brain will
incorporate additional modules allowing language
processing and more advanced inference -- the
next step on the path from virtual dogs to
human-level virtually-embodied AGIs
54
Stages of Development of an AGI
Full Self-Modification

Reflexive
Deep understanding and control of self structures
and dynamics
Formal
Abstract reasoning and hypothesizing. Objective
detachment from phenomenal self.

Concrete
Rich variety of learned mental representations
and operations thereon. Emergence of phenomenal
self.
Infantile
Making sense of and achieving simple goals in
sensorimotor reality. No self yet.
55
Intelligence
56
Intelligence
57
Intelligence
58
Within thirty years, we will have the
technological means to create superhuman
intelligence. Shortly thereafter, the human era
will be ended When greater-than-human
intelligence drives progress, that progress will
be much more rapid
The Coming Technological Singularity Verner
Vinge (1993)
59
I set the date for the Singularity- representing
a profound and disruptive transformation in human
capability- as 2045. The nonbiological
intelligence created in that year will be one
billion times more powerful than all human
intelligence today." The Singularity is Near,
When Humans Transcend Biology - Ray Kurzweil
(2005)