© NOKIAexymach / 10.9.2003 / PHa page: 1 From Machine Cognition to Conscious Machines Dr. Pentti O...
-
Upload
maximilian-baldwin -
Category
Documents
-
view
216 -
download
0
Transcript of © NOKIAexymach / 10.9.2003 / PHa page: 1 From Machine Cognition to Conscious Machines Dr. Pentti O...
© NOKIA exymach / 10.9.2003 / PHa page: 1
From Machine Cognition to Conscious Machines
From Machine Cognition to Conscious Machines
Dr. Pentti O A Haikonen,
Principal Scientist, Cognitive Technology
Nokia Research Center
Exystence Workshop
Machine Consciousness: Complexity Aspects
© NOKIA exymach / 10.9.2003 / PHa page: 2
Why machine cognition?
About intelligence, understanding and cognition
A model for cognitive and thinking machines
Machine cognition and consciousness; -one sided
coins or egg and chicken?
The Outline of the Story
© NOKIA exymach / 10.9.2003 / PHa page: 3
Many of today’s products are so complicated that the user
cannot possibly control all the involved processes, the product
itself must take care of these and leave only higher level
control and decisions to the user.
This is achieved by preprogrammed rules and algorithms that
are sometimes called embedded intelligence.
It is seen that blind algorithms are only a limited solution, more
complex context awareness, machine understanding, is
required.
Towards More Sophisticated Information Technology Products
© NOKIA exymach / 10.9.2003 / PHa page: 4
The machine as a tool:-The user can execute an action with the machine
The machine as an automaton:-The user (or condition) can initiate action sequences
The machine as an agent:-The user can request a context dependent function
The machine as an autonomous agent:-The machine executes context dependent actions as is deemed necessary by (heuristic) set of rules
The machine as a cognitive agent:-The machine understands and is aware; is able to execute tasks requiring real intelligence and thought
Levels of Machines; One more Step to Go
© NOKIA exymach / 10.9.2003 / PHa page: 5
Speech and language; recognition, understanding and translation
Vision; visual episode understanding, prediction
Unified sensory information understanding
Non-indexed data base search and information compilation
Improved Artificial Intelligence, artificial creativity
Personal artificial assistants and companions
Autonomous robots;
sterile nurses that do not fall ill, rescue robots, etc.
Security, defense and law enforcement
Etc.
Machine Understanding of Meaning and Context Will Enable New Possibilities
© NOKIA exymach / 10.9.2003 / PHa page: 6
From speech recognition to speech understanding
From pattern recognition to scene understanding
From text parsing to story understanding
From statistical "learning" to cognitive learning
From numerical simulation to free imagination
What We Want: Cognitive Information Technology
or
Human-like Information Processing
© NOKIA exymach / 10.9.2003 / PHa page: 7
GOFAI - The brain is a computer; human-like intelligence
and cognition via programs and algorithms?
Artificial Neural Networks; human-like intelligence via
statistical computing?
DSP; Systems with sensors, sensory information
represented by numeric values - processing by transforms,
filtering, etc. with partly parallel architectures.
Semantic Networks; understanding via classification and
indexing?
Traditional Models and Tools
© NOKIA exymach / 10.9.2003 / PHa page: 8
Humans surpass the computer in everyday tasks
because humans are intelligent and are able to
understand.
But, what is intelligence and understanding?
Traditional Methods have not Provided
True Intelligence and Understanding
© NOKIA exymach / 10.9.2003 / PHa page: 9
What is Intelligence?
No intelligence is needed if you can use this by
following the instructions only
Instruction
booklet
© NOKIA exymach / 10.9.2003 / PHa page: 10
RIP GOFAI
Intelligence is what we use when rules do not help. This excludes the possibility of rule-based AI
What is Intelligence
© NOKIA exymach / 10.9.2003 / PHa page: 11
Understanding is not that Simple
For instance - Episodic Understanding:
NOT tape recorder type storage and playback
BUT the ABILITY to
-Answer questions about the subject;
-what is where
-what is happening
-who is doing what to whom, etc.
-Paraphrase; describe in own words
-Detect contradictions
-Predict what happens next, what is possible
-Evaluate significance, is this good or bad
-Give reasons for present situation, Etc.
.
© NOKIA exymach / 10.9.2003 / PHa page: 12
Understanding Necessitates the Grounding of Meaning
Real world concepts must be grounded to real world entities.
-This calls for a perception process
Concepts must be connected to other concepts.
-This calls for associative cross-connections
The general model of cognition provides these functions
and more.
© NOKIA exymach / 10.9.2003 / PHa page: 13
The General Model of Cognition
Environment Perception process Internal process
percepts of:-environment-inner states
objects
actions
situationmatch/mismatch/novelty detection
tasks, goals, needsmemories
learned routines
predictionreasoningplanned actionjudgement
ReactionsActions
etc.
experience
relationships
emotionsemotionalevaluation
© NOKIA exymach / 10.9.2003 / PHa page: 14
The Cognitive Model as an Associative Structure
© NOKIA exymach / 10.9.2003 / PHa page: 15
Representation of Information or
the Power of Power Sets
The idea behind distributed signal representations:
The set of all subsets -the power set- is always larger than
the original set. Therefore a limited number of original set
members -here the basic signals- can give rise to a much
larger number of subsets -possible signal combinations-
allowing thus the representation of large number of
different cases with only limited number of basic signals.
© NOKIA exymach / 10.9.2003 / PHa page: 16
Distributed Representations and Associative Processing
Signals and signal sets carry meaning
Individual signals correspond to elementary features
Signal sets or arrays correspond to entities
Entities can be associated together by linking the
corresponding signal arrays
An entity can be evoked by incomplete or slightly different
signal array -”the closest guess”
Also episodes, signal set sequences, can be handled
© NOKIA exymach / 10.9.2003 / PHa page: 17
Distributed Representations and Associative Processing Go Well Together
Provided that
Combinatorial explosion is avoided by attention; a mechanism
that limits the actual connections by relevance and
importance, etc. Hence the eventual need for emotional
significance.
Interference -the false evocation of undesired signals- is
controlled, various methods exist.
© NOKIA exymach / 10.9.2003 / PHa page: 18
environment
sensors & pre-processing
rawdistributed signals
innerprocesses
feedback
perception process
percepts
responses
The Outline of a Conscious Machine
© NOKIA exymach / 10.9.2003 / PHa page: 19
The General Architectureperceptpreprocesssensor
preprocesssensor
preprocesssensor
preprocesssensor
Body position
Touch subsystem
Auditory subsystem
Visual subsystem
system reactions
System
perception process
perception process
perception process
perception process
perception process
neuron group
neuron group
neuron group
neuron group
neuron groupsmell, taste, pain, etc.
motor actions threshold
threshold
percept
percept
percept
percept
© NOKIA exymach / 10.9.2003 / PHa page: 20
Characteristic Properties of the Model
Each modality works on its own and produces streams of percepts about environment and internal states.
Modalities are associatively cross-connected, therefore the activity of one modality may be reflected in the other modalities; percepts may be named and labeled, names may evoke corresponding percepts…the activity of one modality may be memorized and reported in terms of other modalities, etc.
Attention determines which percepts are accepted for further action. Attention is controlled by signal intensity and thresholds, these are controlled by e.g. emotional significance.
Pain and pleasure are system reactions that affect attention.
The flow of inner speech and inner imagery is supported.
© NOKIA exymach / 10.9.2003 / PHa page: 21
How do we know if the machine is conscious? There may be
some telltale symptoms that we could look for.
For instance Prof. Aleksander lists five axioms:
1) sense of place,
2) imagination,
3) directed attention,
4) planning,
5) decision/emotion
In the following a rather similar list is given perhaps with
some twists.
Consciousness in the Machine?
© NOKIA exymach / 10.9.2003 / PHa page: 22
-Does the machine have mental content that is about something?
-Is the machine able to report its mental content to itself (and others) and does it recognize the ownership of the same?
-Is the machine able to make the difference between the environment and the machine self?
-Does the machine have (episodic) sense of time?
-Does the machine bind its present experience to personal history and expected future? (“the flow of existence”)
-Is the machine aware of its own existence?
-The “hammer test” of phenomenal awareness: Does the machine feel pain?
Consciousness in the Machine?
© NOKIA exymach / 10.9.2003 / PHa page: 23
And finally,
if the machine were to genuinely ask:
Where did I come from?
Then we would know that we are into something deep.
Consciousness in the Machine?
© NOKIA exymach / 10.9.2003 / PHa page: 24
In this model understanding arises from the processing with
meaning -on the other hand meaning-carrying signal arrays
are intentional, a supposed prerequisite for consciousness.
Here also the cross-modality binding and reporting -hallmarks
of consciousness- arise from the requirements of cognition.
Therefore, are true cognition and consciousness connected or
separate properties?
Thus, would the proper realization of cognition automatically
result in some kind of consciousness (Or do zombies exist)?
Cognition and Consciousness; Which Comes First?
© NOKIA exymach / 10.9.2003 / PHa page: 25
Dr. Pentti O A Haikonen, Principal Scientist, Cognitive Technology
Nokia Research Center
From Machine Cognition to Conscious Machines
Thank You
for Your Attention!
© NOKIA exymach / 10.9.2003 / PHa page: 26
-end of show-