Software Agent 2009 04 09 Seunghyun Lee David Gamez Consciousness and Cognition vol17 pp 887910 2007 Contents Introduction Classification of Machine Consciousness MC1 MC2 MC3 and MC4 ID: 364962
Download Presentation The PPT/PDF document "Progress in Machine consciousness" 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
Progress in Machine consciousness
Software Agent2009. 04. 09Seunghyun Lee
David Gamez,
Consciousness and Cognition
vol.17, pp.
887-910, 2007Slide2
ContentsIntroductionClassification of Machine Consciousness
MC1, MC2, MC3, and MC4Research ProjectsRelationship with Other AreasCriticisms
Issues and Potential Benefits
1
Slide3
IntroductionMachine consciousnessTest theories of consciousness using computer
modelsCreate more intelligent machines that might actually have phenomenal states“Artificial consciousness”, “digital sentience”
Breaking machine consciousness into four areas
2
Category
Associated Subject
MC1
External behavior
MC2
Cognitive characteristics
MC3
Architecture
MC4
Phenomenally
consciousnessSlide4
Classification of Machine Consciousness MC1(External behavior
)Goal Replicate conscious human behavior
Large lookup table /
zombie
robot
Example
Turing
Test
3
Unconscious
behavior
Conscious behavior
Feature
-Automatically carried out
-Limited amount of behavior
-Complex activities
-New behaviors can
only be learnt when consciousness is present
Example
Muscle contractions while
walking, epileptic seizure
Driving home from work, interpersonal dialogSlide5
Classification of Machine ConsciousnessMC2(Cognitive characteristics)Goal
Research on connection between consciousness and cognitive characteristicsImagination, emotion, and selfMetzinger’s 11 constraints on consciousness
(1) Global availability
(2) Activation within a window of presence
(3) Integration into a coherent global state
(4) Convolved holism
(5) Dynamicity
(6)
Perspectivalness
(7) Transparency
(8) Offline activation
(9) Representation of intensities(10) “Ultrasmoothness
”: Homogeneity of simple content(11) Adaptivity
Alexsander’s
five cognitive mechanisms
4
Slide6
Classification of Machine ConsciousnessMC3 (Architecture)
Goals Simulation of architectures related to human consciousnessGlobal workspace(Baar
),
neural synchronization(Crock)
MC4(
Phenomenally
consciousness)
Phenomenally consciousness?We have phenomenally conscious states when we see, hear, smell,
taste
and have pains. (Block 1995: 230)
GoalsResearch on machines that have real phenomenal experiences that are actually conscious themselvesSystem based on biological neurons
5
Slide7
Depiction
Represent elements of the world(perceptual states)
Imagination
Recall parts of the world or create sensations
Attention
Select which parts to be depicted or imagined
Planning
Control sequences of states to plan actions
Emotion
Evaluate planned actions and determine the ensuing action
Research
Project
Five
axioms(
Alekxsander
,
Dunmall
, 2003)
Kernel
Architecture(
Alekxsander
, 2005)
6
Axioms and Neural
Representation Modeling Slide8
Research Projects
Main focus of this project Cognitive
, architectural and phenomenal aspects of machine consciousness (
MC2~4
).
Constitution
CRONOS, SIMNOS, biologically inspired visual system,
SpikeStream
7
CRONOS
<CRONOS>
<SIMNOS>Slide9
Research Projects Approach 1(Holland, 2003)
Focus on internal modelTestSIMNOS as an internal model of CRONOS
CRONOS
eyes obtains information from environment
Update SIMNOS
Internal model : ‘offline’
‘imagine’ mode before selected action is carried out
Approach
2(Gamez)
Development of spiking neural network
that controls eye movement
Generates eye movement spontaneously to the different partLearns the association between the eye’s position and a visual stimulus Emotional systemNegative object ‘imagination’ mode inhibit sensory input and motor output
Cognitive characteristic(MC2), neural correlated architecture(MC3)
8
CRONOSSlide10
Research ProjectsBrooks, Breazeal et al.(1998)
Constitution4 cameras, 2 microphones, and many piezoelectric touch sensorsA number of hard
wired innate
reflexes
Emotional
System
Independent projects
Joint attention, theory of mind, social
interaction, dynamic human-like arm motion, and multi-modal coordinationRelationJoint attention, theory of mind
(MC1
)
Cog’s emotional system(MC2)LimitMany individual human behaviors are implemented Active all together incoherence and interference
9
CogSlide11
Research Projects Simulated infant(Cotterill
, 2000) Controlled by a biologically inspired neural systemPremotor
cortex, supplementary motor
cortex, frontal eye fields, thalamic nuclei,
hippocampus and
amygdala
Interconnection : based on anatomical
connectivity
SimulationBlood glucose measurement, milk, urine
Sustain avoiding discomfort
Goal
Identify neural correlates of consciousnessRelationNeural correlates of consciousness(MC3), (MC4)
10
CyberChildSlide12
Research Projects
Approach 1(Holland and Goodman, 2003)Test the role of internal model in consciousnessUsing ARAVQ(Adaptive Resource-Allocating Vector
Quantizer
)
Graphical representations of inner states
Experiment
Wall following and obstacle avoidance behavior
ARAVQ build up
concepts forms internal model
Good performance
Some of the internal models in humans are integrated into conscious cognitive
states(MC2)
11
Khepera
modelsSlide13
Research Projects Approach 2(Ziemke
et al., 2005)ImaginationUsing simple neural networkConstitutionSensorimotor
module :
Avoid
obstacle, perform fast straightforward motion
Prediction module :
Predict
the sensory input of the next time step
‘Imagined’ sensory inputs produced very similar behavior to real sensory inputMC2
12
Khepera
modelsSlide14
Research Projects
Global workspace theory(Baar, 1988)
13
Global Workspace ModelsSlide15
Research Projects IDA naval dispatching System(Franklin, 2003)
Assign sailors to new billetsFunctions are carried out using codeletsApparatus for consciousnessCoalition
manager
S
potlight controller
B
roadcast manager
A number of attention
codeletsMC1, MC2, MC3 Neural simulations(
Dehaene
et al
., 1998)Stroop taskPredictions about brain imaging patterns Attentional blink Explained using the theory about the implementation of a global workspace in the brain
MC2, MC3
14
Global Workspace ModelsSlide16
Research ProjectsBrain-inspired cognitive architecture(Shanahan, 2006)
Functionally analogous components to brain structure
Enable the system to follow
chains of association
E
xplore the potential
consequences prior to the action
Experiment
Webot
and Khepera robotLow level actions and preferences for cylinders with different color
Produced behavior(MC1), imagination and emotion(MC2), based on global workspace model(MC3)
15
Global Workspace ModelsSlide17
Research ProjectsLanguage and agent-based architecture(Angel, 1989)Three
attributes for conscious system1. Independent purpose regardless of its contact with other agents.2. The ability to make interagency attributions
on a pure or natural basis.
3. The ability to
learn from scratch
significant portions of some natural language, and the ability to use these elements in satisfying its purposes and those of its interlocutors.
N
obody
has implemented with this model Inner speech(Steels, 2003)Experiments in which two robotic heads watched scenes and played a language-game that evolved a lexicon or grammar
R
ehearse
future dialogue, submit thoughts to self-criticism, and conceptualize and reaffirm memories of past experiencesMC2
16
Language and AgencySlide18
Research Projects Cognitive approach(Haikonen
, 2003)System intended to develop emotion, transparency, imagination,and inner speech
Sensory modules
Main idea
Percepts
Conscious
different modules cooperate in
unison, focus on the same entity,
forms associative memories
MC1~4
17
Cognitive ArchitectureSlide19
Research Projects Schema-based model(Samsonovich
and DeJong, 2005)Based around schemasConstrained by a set of axioms Axioms correspond to the
system’s ‘conscious’ self
MC1, MC2, but not MC3
Cicerobot
(
Chella
and
Macaluso
)
Museum
tour guide robotBased around an internal 3D simulation
plan actionsConscious cognitive architecture(MC2),
control
the robot(MC1)
18
Cognitive ArchitectureSlide20
Research ProjectsSynthetic phenomenologyNew
area of research on machine consciousnessDevelop artificial systems which are capable of conscious states and the description of their phenomenology
when and if this
occurs
Challenges
Develop
s
ystems which be capable of phenomenal states
“To be synthetically phenomenological, a
system S must contain machinery that represents what the world and the system S within it
seem like
, from the point of view of S’’(Aleksander and Morton, 2006)Find ways of describing phenomenal states when and if they occur Graphical representations of
Kheperas’ inner states(Holland, 2003)Distinguish machine’s phenomenal and non-phenomenal states
which internal states are likely to be conscious?
19
Slide21
Relationship with Other AreasStrong and weak AI(Searle, 1980)Weak AI : Powerful tool when we study mind (modeling)
MC1~3Strong AI : Programmed computer is mind itself MC4Artificial general intelligence
Goal : Replicate human intelligence completely
ex) chess playing
MC1 : Conscious human behavior
Psychology, neuroscience and philosophy
P
sychology : Build also computer cognition model
not only conscious state but also othersNeuroscience : Trend that tests theories about attention and consciousness with neuronsPhilosophy : Common in the use of logic
20
Slide22
Criticisms The hard problem of consciousnessEasy problem : D
iscriminate, integrate information, report mental states, focus attention etc…(MC1, MC2, MC3)Hard problem : Explaining phenomenal
experience(MC4)
Many
theories, but no real idea to solve
Consciousness
is
non-algorithmic
Processing of an algorithm is not enough to evoke phenomenal awareness because of subtle and largely unknown physical principles
What computers still cannot
do
Fact based system cannot solve human intelligence which depends on skills, a body, emotions, imagination and other attributes that cannot be encoded into long lists of facts
21
Slide23
Potential Benefits and Issue Potential benefits
MC1 : Help people to produce more imitation of human behaviorex) chatterbots
MC2 : Machine which understand human world and language in a human-like way can assist people
MC3 :
H
elp people to understand how the brain processes information, so that it is able to develop prosthetic interfaces to restore visual, auditory or limb functions
MC4 :
H
elp people to understand the phenomenal states of very young or brain-damaged people who are incapable of communicating their experiences in language
22
Slide24
Potential Benefits and IssueIssuesCan machines take over and enslave humans?
How we should treat conscious machines?How should it be the legal status of conscious machines? Discussion
23