simia Gabriel von Max Prague painter 18401915 Towards C omputational Models of Artificial Cognitive Systems That Can in Principle Pass the Turing test Jiri Wiedermann Institute of Computer Science Prague ID: 241757
Download Presentation The PPT/PDF document "Monkey Before the Skeleton (Ecce" is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Monkey Before the Skeleton (Ecce
simia
),
Gabriel von Max, Prague painter (1840-1915)Slide2
Towards Computational Models
of Artificial Cognitive Systems
That Can, in Principle, Pass the Turing test
Jiri WiedermannInstitute of Computer Science, Prague Academy of Sciences of the Czech Republic
Partially
supported GA CR grant No. P202/10/1333
SOFSEM 2012 January 21-27, 2012
Spindleruv
MlynSlide3
``I believe that in about fifty years' time it will be possible, to program computers, with a storage capacity of about 100
kB
, to make them play
the imitation game so well that an average interrogator will not have more than 70 % chance
of making the right identification after five minutes of questioning.
The original question, "Can machines think?" I believe to be too meaningless to deserve discussion. Nevertheless I believe that at the end of the century the use of words and general educated opinion will have altered so much that
one will be able to speak of machines thinking
without expecting to be contradicted."
From the discussion between Turing and one of his colleagues (M. H. A. Newman, professor of
mathematics at the Manchester University):
Newman
: I should like to be there when your match between a man and a machine takes place,
and perhaps to try my hand at making up some of the questions. But that will be a long time from
now, if the machine is to stand any chance with no questions barred?
Turing
: Oh yes, at least 100 years, I should say.Slide4
Three heretic ideas:
We already have a sufficient knowledge to
understand the working of interesting minds achieving a high-level cognition
Achieving a higher-level AI is not a matter of a fundamental scientific breakthrough but rather a matter of exploiting our best theories of artificial minds, and a matter of scale, speed and technological achievements
It is unlikely that thinking machines will be developed by purely academic research
since it is beyond its power to concentrate the necessary amount of man power and technology. Approaches to mind understanding:Understanding by philosophying Understanding by designing (specifying)Understanding by constructingSlide5
Outline
Current state: Watson the Computer vs. humanoid robotic systems
Winds of Change
Escaping the Turing testEscaping BiologismInternal World Models
Mirror neuronsGlobal Workspace Theory(
Dis)solving the Hard Problem of ConsciousnessEpisodic MemoriesReal Time Massive Data ProcessingComprehensive and Up-To-Date Models of Cognitive SystemsHUGO: A Non-Biological Model of a Conscious Agent System
Conclusions – lessons from what we
have seenSlide6
Watson
-
an AI system capable to answer the questions stated in natural language
Jeopardy
!
(in the CR – the TV game „Riskuj!“) – given an answer one has to guess the question.
E.g.:
5280 (
how many
feets
has a mile), or 79 Wistful Vista (address of
Fibber
a
nd
Molly
McGee
)
Category:
General Science
Clue:
When hit by electrons, a phosphor gives off
electromagnetic energy in this form.Answer: Light (or Photons)Category: Lincoln BlogsClue: Secretary Chase just submitted this to me for the third time; guess what, pal. This time I’m accepting it.Answer: his resignationCategory: Head NorthClue: They’re the two states you could be reentering if you’re crossing Florida’s northern border.Answer: Georgia and Alabama
Category: Rhyme TimeClue: It’s where Pele stores his ball.Subclue 1: Pele ball (soccer)Subclue 2: where store (cabinet, drawer, locker, and so on)Answer: soccer locker
Source
: AI
Magazine
,
Fall
2010Slide7
Winds of Change
New trends in theory:
escaping biologism
escaping the Turing Test strengthening the position of embodiment: a common sensorimotor
basis for phenomenal and functional consciousness evolutionary priority of phenomenal consciousness over functional one
internal world models, mirror neurons global workspace theory episodic memoryTechnological progress: maintenance of supercritical volumes of data, and
searching and retrieval of data by supercritical speed Slide8
A shift in popular thinking about artificial minds - people generally accept that computers can think (albeit in a different sense than some philosophers of mind would like to see)
John Searle
: “
Watson Doesn't Know It Won on 'Jeopardy!' IBM invented an ingenious program—not a computer that can think.”
Noam Chomsky: “Watson understands nothing. It’s a bigger steamroller. Actually, I work in AI, and a lot of what is done impresses me, but not these devices to sell computers.”
What these gentlemen failed to see
is the giant leap
from the formal rules of the chess playing to informality of Jeopardy! rules…
J.R. Lipton
: Big insight – a program can be immensely powerful even if it is
imperfect. Slide9
A new trend: escaping biologism
Rodolfo
Llinas (a prominent neuroscientist):“I must tell you one of the most alarming experiences I've had in pondering brain function.... that the octopus is capable of truly extraordinary feats of intelligence… most remarkable is the report that octopi may learn from observing other octopi at work. The alarming fact here is that the organization of
the nervous system of this animal is totally different from the organization we have learned is capable of supporting this type of activity in the vertebrate brain....
there may well be a large number of possible architectures that could provide the basis of what we consider necessary for cognition and
qualia.... Many possible architectures for cognition
Why should we only think about human brain when
designing artificial minds?Slide10
Turing test is explicitly anthropomorphic.Russell and Norvig: "aeronautical engineering texts do not define the goal of their field as 'making machines that fly so exactly like pigeons that they can fool other pigeons’”.
A new trend: escaping the Turing test
All minds
Human
mind
Alien
minds
Animal
minds
Artificial
mindsSlide11
A new trend: Internal World Models
IWMs capture a “description” of that (finite) part of the world and that part of the self which has been “learned” by agent’s
sensori
-motor activities. An IWM is fully determined by the agent’s embodiment and is automatically built during agent’s interaction with the real world.
Mechanisms situating an agent in its environment ; they determine the syntax and the semantic of agent behavior and perception in its environment
Finite
control
Sensory-motor
units
World model
The body
(Infinite) stream of inputs generated by sensory-motor interaction
A virtual inner world in which an agent can thinkSlide12
A new trend: Mirror neurons – a mechanism for “mind reading” of other subjects
“the discovery of mirror neurons in
the frontal lobes of monkeys, and
their potential relevance to human brain evolution is the single most important ``unreported“ (or at least,
unpublicized) story of the decade. I predict that mirror neurons will do for psychology what DNA did for
biology: they will provide a unifying framework and help explain a host of mental abilities that have hitherto remained mysterious and inaccessible to experiments“V.S. Ramachandran
Mirror neurons
: are active when a subject performs a specific action as well as when the subject observes an other or a similar subject performing a similar action (
Rizzolatti
, 199x)
Slide13
A new trend: Global Workspace Theory
a simplistic, very high-level cognitive architecture that has been developed by
B. J. Baars
by the end of the last century to explainemergence of a conscious process from large sets of unconsciousprocesses in the human brain.
The GWT can successfully model a number of
characteristics of consciousness, such as its role in handling novel situations, its limited capacity, its sequential nature, and its ability to trigger a vast range of unconscious brain processes.Interesting:
Watson the Computer works according to the GWTSlide14
A new trend: evolutionary approach to phenomenal consciousness (Inman Harvey)
A naive “incremental” approach to create phenomenal consciousness:
Create a “zombie” with functional consciousness (the easy problem)
Add the extra ingredient to give it a phenomenal consciousness
(the hard problem)
“evolutionary approach allows emulation without comprehension” Slide15
A new trend: a common sensorimotor basis for phenomenal and functional consciousness
Source: How to build a robot that feels.
J.Kevin
O'Regan
,Talk given at
CogSys
2010 at ETH Zurich
A
sensorimotor
interaction with the environment involving corporality, alerting capacity, richness,
insubordinateness
, and the self
Instead of thinking of the brain as the generator of feel, feel is considered as a way of interacting with the worldSlide16
A new trend: Episodic Memory
An agent without episodic memory is like
a person with amnesia
Episodic memory systems allow
“mental time travel”
and can support a vast number of cognitive capabilities based on inspecting memories from the past that are ``similar" to the present situation, such as noticing novel situations, detecting repetitions,
virtual sensing (reminded by some recall),
future action modeling,
planning ahead,
environment modeling,
predicting success/failure, managing long term goals, etc. is what people ``remember", i.e., the contextualized information about autobiographical events (times, places, associated emotions), and other contextual knowledge that can be explicitly stated.
Efficient management and retrieval from episodic memories is a case for real-time massive data processing technologies.
(Drawing by Ruth
Tulving
)Slide17
A new trend: intelligence might be a matter of scale and speed: maintaining supercritical volumes of data and their searching and retrieval by supercritical speed (cf. episodic memories).
Element
Number
of cores
Time to answer one Jeopardy! question
Single core
1
2 hours
Single IBM Power 750 server
32
<4 minSingle rack (10 servers)
320
<30 seconds
IBM Watson (90 servers)
2 880
<3 seconds
Memory:
20 TB
200 million pages
(~1
000
000 books)
~1 000 000 million lines of code5 years development(20 men) A lesson from Watson the Computer: intelligence might not only be a matter of suitable algorithms, but also, and mainly so, of the ability to accumulate (e.g., via learning and episodic memories storing), organize, and exploit large data volumes representing knowledge at a speed matching the timescale of the environmental requirements (real time data processing).Slide18
A new trend: Comprehensive and up-to-date models of cognitive systems
An urgent need of
situatedness
via embodiment
(from J. A. Comenius,
Orbis
pictus
, 1658)
An embodied cognitive agent
is a robot i.e., an
embodied computer
, which is a computer equipped by
sensors
by which it “perceives” its environment and by
effectors
by which it interacts with its environment
Nuremberg funnel,
Harsdörffer, Georg Philipp:
Poetischer Trichter,
Nuremberg
1648-1653Slide19
HUGO: a Non-Biological Model of an Embodied Conscious Agent
From: J. Wiedermann: A High Level Model of an Embodied Conscious Agent, IJSSCI, 2, 2010
Semantic world model
Syntactic world model
Global workspace
Mirror net
Episodic
memorySlide20
A high-level schema of a robot:
Finite control (a computer)
Sensory-motor units
(Infinite) stream of inputs generated by sensory-motor interaction
World model
Real world
The body
Mechanisms
situating the agent in its environment
must be considered: internal world modelsSlide21
The central idea: Educating and Teaching a Robot
The purpose of educating and teaching an agent is to build its internal world model
The internal world model gives a “description” of that (finite) part of the world (inclusively of agent’s (it)self) which has been “learned” by agent’s S-M activities.
The model is fully determined by the agent’s embodiment and is automatically built during agent’s interaction with the real worldSlide22
The idea of two cooperating world models in cognitive systems
“action”
Dynamic world model:
sequences of
sensorimotor
information
Controls the agent’s behavior
Static world model:
Elements of a coupled
sensory-motor
information; responsible for situating the agent
Real world
“cognition”
Motor instructions
perception
Sensory-motor unitsSlide23
Grounding
Abstract
concepts
U
nits of S-M
information
(World’s
“syntax”)
Embodied
concepts
S-M
units
Motor instructions
Multimodal
information
Perception
Motor instructions
Symbolic
level
Sub-symbolic level
Control unit
Body
Environment
Mirror net
An architecture of an
embodied cognitive
agentSlide24
The task of the syntactic world model:
Coupling
the motor instructions with the perception information into so-called multimodal information;
Learning frequently occurring multimodal information from the coupled input streams (one coming from the dynamic model and one from the S-M units)
Associative retrieval: a partial, or “damaged”, or previously “unseen” incoming multimodal information gets completed so that it
corresponds to the “most similar” previously learned information; the result
captures the instantaneous agent’s
situationThe task of the semantic world model:Learning (mining) and maintaining the knowledge from the data-stream of multimodal
informa
tion
delivered by static (syntactic) world model
Realizing the intentionality
:
with each unit of multimodal information a sequence of actions (motor commands) –
habits
- gets associated which can be realized in the given context; Slide25
Mirror neurons: are active when a subject performs a specific action as well as when the subject observes an other or a similar subject performing a similar action (
Rizzolatti
, 199x)A generalization
: … a set of neurons which are active when a subject performs any frequent action as well as when only partial information related to that action is available to the subject at hand
Implementing the syntactic world model:
Visual inf. Aural inf. Haptic Propriocept.
Multimodal
information
Learns frequently occurring conjunctions of related input information
It gets activated when only partially excited (by one or several of its inputs)
Works as
associative memory,
completing the missing input information
Mirror net forms and stores (pointers to)
episodic memories
The basis for understanding imitation learning, language acquisition,
thinking, consciousness.Slide26
What knowledge is mined and maintained in a dynamic world model:
often occurring concepts
resemblance of concepts contiguity in time or place
cause and effectAn algebra of thoughts…
David Hume 1711-1766
Cognitive tasks:
Simple conditioning
Learning of sequences
Operand
conditioning
(by rewards and punishment)Imitation learningAbstraction formingHabits formation, etc.
“Hume’s test” for intelligenceSlide27
Previously
activated
concepts
Passive
concepts
Newly activated concepts
Multimodal information
Currently
activated
concepts
A
cogitoid
: an algorithm
building a neural net for
knowledge-mining
from
the
flow
of multi-modal information
Emotions
Excitatory and inhibitory links
aaaa
affect
Wiedermann 1999
Implementing the dynamic world model
Habits: often followed
chains of conceptsSlide28
What both world models jointly do for an agent:
A mechanism enabling
imitation of activities of other agents (without
understanding)A
germ of awareness – a mechanism for distinguishing between one’s own action, and that of an observed agentA mechanism of empathy
A
substrate for a mechanism for
predic
ting the results
of an agent’s own or observed actions via their “simulation” in the virtual model of the known part of the real worldUnderstanding: an agent “understands” its actions in terms of their embodiment in terms of habits (and thus: of S-M actions plus associated emotions)
Phenomenal consciousness
(according to
O’Regan
) as a habit of conscious awareness of
performing one’s own skills
Humanoid Robot
Mahru
Mimics a Person's Movements in Real Time
A person wears the motion tracking suit while performing various tasks. The movements are recorded and the robot is then programmed to reproduce the tasks while adapting to changes in the space, such as a displaced objects.Slide29
The birth of
communication and speaking
By indicating a certain action an agent
broadcasts a visual information
which is completed by the empathy and prediction mechanism of an observing agent into the intended action
Formation of the self conceptPossibility for emotions
to enter the
game
The birth of the
body language
Adding of articulation (vocalization) and gesticulation tempering
The verbal component of the language gets associated with the motor of speech organs and prevails over gesticulation
Development of
episodic memory
management and retrieval mechanismsSlide30
The birth of thinking
c
ogitoid
Mirror
neuro
ns
Motor
instructions
Multimod
al
informa
tion
Subsequent
decay of whatever motor activity
(
of vocal organs)
Perception suppressing
Switching-off
motor
instruction
realization
Mirror neurons complete motor instructions by missing perception learned by experienceWiedermann 2004Beginning of
thinking as a habit of speaking to oneselfAn agent operates similarly as before, albeit it processes “virtual” data. It works in an „off-line“ mode, it is virtually situatedSlide31
The birth of
functional consciousness
The agents are said to possess
artificial
functional consciousness
iff their communication abilities reach such a level that the agents are able to fable on a given theme.More precisely, the conscious agents can
Communicate in a
high-level language
Verbally
describe
past and present experience, and expected consequences of future actions, of self or of other agentsRealize a certain activity given its verbal high-level descriptionExplain the meaning of notions
Learn
new notions and new languages
Consciousness is a
big suitcase
M.
MinskySlide32
A sketch of the evolutionary development of
cognitive abilities, consciousness included
Phenomena
l
consc
.
Funct
.
consc
.
From: J. Wiedermann: A High Level Model of an Embodied Conscious Agent, IJSSCI, 2, 2010
Slide33
A thinking machine: a de-embodied robot
c
ogitoid
Mirror
neuro
ns
A brain in a vat
A robot’s thinking mechanism
in a computerSlide34
Lessons from what we have seen
Achieving a higher-level artificial intelligence no longer seems to be a matter of a fundamental scientific breakthrough
but rather a matter of exploiting our best algorithmic theories of thinking machines supported by our most advanced robotic and real time data processing technologies.
An artificial cognitive system is quite a complex system with only a few components none of which could work alone and none of them could be developed separately;
It is unlikely that thinking machines will be developed by purely academic research since it is beyond its power to concentrate the necessary amount of man power and technology. This cannot be accomplished by large international research programs
either since a dedicated long-term open-ended effort of many researchers concentrated on a single practically non-decomposable task is needed.
It seems to be a unique strategic opportunity for giant IT corporations
.
The road towards thinking machines glimpses ahead of us and it only is a matter of money whether we set off for a journey along this road.Slide35
The EndSlide36
Caspar David Friedrich,
Giant Mountains, cca 1830