progress in machine consciousness software agent 2009. 04. 09 seunghyun lee 887-910, 2007 david...

24
Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee David Gamez, Consciousness and Cognition vol.17, pp.887-910, 2007

Upload: conrad-george

Post on 11-Jan-2016

213 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

Progress in Machine consciousness

Software Agent

2009. 04. 09

Seunghyun Lee

David Gamez, Consciousness and Cognition vol.17, pp.887-910, 2007

Page 2: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Contents

• Introduction

• Classification of Machine Consciousness– MC1, MC2, MC3, and MC4

• Research Projects

• Relationship with Other Areas

• Criticisms

• Issues and Potential Benefits

2

Page 3: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Introduction

• Machine consciousness– Test theories of consciousness using computer models– Create more intelligent machines that might actually have phenome-

nal states– “Artificial consciousness”, “digital sentience”

• Breaking machine consciousness into four areas

3

Category Associated Subject

MC1 External behavior

MC2 Cognitive characteristics

MC3 Architecture

MC4 Phenomenally consciousness

Page 4: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Classification of Machine Consciousness

• MC1(External behavior)– Goal

Replicate conscious human behavior

– Large lookup table / zombie robot– Example

• Turing Test

4

Unconscious behavior Conscious behavior

Feature -Automatically carried out-Limited amount of behavior

-Complex activities-New behaviors can only be learnt when consciousness is present

Exam-ple

Muscle contractions while walking, epileptic seizure

Driving home from work, inter-personal dialog

Page 5: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Classification of Machine Consciousness

• MC2(Cognitive characteristics)– Goal

Research on connection between consciousness and cognitive characteristics

– Imagination, emotion, and self– Metzinger’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

5

Page 6: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Classification of Machine Consciousness

• MC3 (Architecture)– Goals

Simulation of architectures related to human consciousness– Global 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)

– Goals

Research on machines that have real phenomenal experiences thatare actually conscious themselves

– System based on biological neurons

6

Page 7: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Depiction Represent elements of the world(perceptual states)

Imagina-tion

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)

7

Axioms and Neural Representation Modeling

Page 8: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Main focus of this project – Cognitive, architectural and phenomenal aspects of machine con-

sciousness (MC2~4).

• Constitution– CRONOS, SIMNOS, biologically inspired visual system,

SpikeStream

8

CRONOS

<CRONOS> <SIMNOS>

Page 9: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Approach 1(Holland, 2003)– Focus on internal model– Test

• SIMNOS 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 part• Learns the association between the eye’s position and a visual stimulus

– Emotional system• Negative object ‘imagination’ mode inhibit sensory input and motor output

– Cognitive characteristic(MC2), neural correlated architecture(MC3)

9

CRONOS

Page 10: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Brooks, Breazeal et al.(1998)• Constitution

– 4 cameras, 2 microphones, and

many piezoelectric touch sensors– A 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 coordination• Relation

– Joint attention, theory of mind (MC1)– Cog’s emotional system(MC2)

• Limit– Many individual human behaviors are implemented – Active all together incoherence and interference

10

Cog

Page 11: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Simulated infant(Cotterill, 2000)• Controlled by a biologically inspired

neural system– Premotor cortex, supplementary motor

cortex, frontal eye fields, thalamic nuclei,

hippocampus and amygdala– Interconnection : based on anatomical

connectivity• Simulation

– Blood glucose measurement, milk, urine– Sustain avoiding discomfort

• Goal– Identify neural correlates of consciousness

• Relation– Neural correlates of consciousness(MC3), (MC4)

11

CyberChild

Page 12: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Approach 1(Holland and Goodman, 2003)– Test the role of internal model in consciousness– Using 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 con-scious cognitive states(MC2)

• 12

Khepera models

Page 13: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Approach 2(Ziemke et al., 2005)– Imagination– Using simple neural network– Constitution

• Sensorimotor 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 input

– MC2

13

Khepera models

Page 14: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Global workspace theory(Baar, 1988)

14

Global Workspace Models

Page 15: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• IDA naval dispatching System(Franklin, 2003)– Assign sailors to new billets– Functions are carried out using codelets– Apparatus for consciousness

• Coalition manager• Spotlight controller• Broadcast manager• A number of attention codelets

– MC1, MC2, MC3

• Neural simulations(Dehaene et al., 1998)– Stroop task

• Predictions about brain imaging patterns

– Attentional blink• Explained using the theory about the implementation of a global workspace in the

brain

– MC2, MC3

15

Global Workspace Models

Page 16: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Brain-inspired cognitive architecture(Shanahan, 2006) – Functionally analogous components

to brain structure

– Enable the system to follow

chains of association

– Explore the potential

consequences prior to the action

– Experiment• Webot and Khepera robot• Low level actions and preferences for cylinders with different color

– Produced behavior(MC1), imagination and emotion(MC2), based on global workspace model(MC3)

16

Global Workspace Models

Page 17: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Language and agent-based architecture(Angel, 1989)– Three attributes for conscious system

1. 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 inter-locutors.

– Nobody 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– Rehearse future dialogue, submit thoughts to self-criticism, and

conceptualize and reaffirm memories of past experiences– MC2

17

Language and Agency

Page 18: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

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

18

Cognitive Architecture

Page 19: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Schema-based model(Samsonovich and DeJong, 2005)– Based around schemas– Constrained 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 robot– Based around an internal 3D simulation

plan actions– Conscious cognitive architecture(MC2),

control the robot(MC1)

19

Cognitive Architecture

Page 20: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Research Projects

• Synthetic phenomenology– New area of research on machine consciousness– Develop artificial systems which are capable of conscious states and

the description of their phenomenology when and if this occurs– Challenges

• Develop systems 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 oc-cur

Graphical representations of Kheperas’ inner states(Holland, 2003)

• Distinguish machine’s phenomenal and non-phenomenal states

which internal states are likely to be conscious?

20

Page 21: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Relationship with Other Areas

• Strong and weak AI(Searle, 1980)– Weak AI : Powerful tool when we study mind (modeling) MC1~3– Strong AI : Programmed computer is mind itself MC4

• Artificial general intelligence– Goal : Replicate human intelligence completely

• ex) chess playing

– MC1 : Conscious human behavior

• Psychology, neuroscience and philosophy– Psychology : Build also computer cognition model not only con-

scious state but also others– Neuroscience : Trend that tests theories about attention and con-

sciousness with neurons– Philosophy : Common in the use of logic

• 21

Page 22: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Criticisms

• The hard problem of consciousness– Easy problem : Discriminate, 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 princi-ples

• 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

22

Page 23: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Potential Benefits and Issue

• Potential benefits– MC1 : Help people to produce more imitation of human behavior

ex) chatterbots

– MC2 : Machine which understand human world and language in a human-like way can assist people

– MC3 : Help people to understand how the brain processes informa-tion, so that it is able to develop prosthetic interfaces to restore vis-ual, auditory or limb functions

– MC4 : Help people to understand the phenomenal states of very young or brain-damaged people who are incapable of communicat-ing their experiences in language

23

Page 24: Progress in Machine consciousness Software Agent 2009. 04. 09 Seunghyun Lee 887-910, 2007 David Gamez, Consciousness and Cognition vol.17, pp.887-910,

S FT COMPUTING @ YONSEI UNIV . KOREA

Potential Benefits and Issue

• Issues– Can machines take over and enslave humans?– How we should treat conscious machines?– How should it be the legal status of conscious machines?

• Discussion

24