Download AI - Department of Computer Science

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts
no text concepts found
Transcript
Snapshots of
AI methods and applications
Agnar Aamodt and Keith Downing
Institutt for datateknikk og informasjonsvitenskap
Seksjon for Intelligente Systemer
NTNU
A. Aamodt, NTNU-IDI
Hva er “Kunstig intelligens” – 1
“AI = Things that make you go WOW!”
eller…??
vel, mer edruelig - om enn litt kjedeligere - så er kjerneideen:
“AI = Representation + Search”
•The concept of search plays an important role in science and
engineering
• In one way, any problem whatsoever can be seen as a search for
“the right answer”
A. Aamodt, NTNU-IDI
Example applications
 Software:
• Pro-aktive beslutningsstøttesystemer
• Automatisk data-analyse
• Lærende systemer, f.eks.:
– Anbefalingssystemer
– AI i spill
– Ansiktsgjenkjenning
• Naturlig språk
• Robotnavigering, syn, planlegging
• Adapterende GUI
• ...
A. Aamodt, NTNU-IDI

Embedded systems
– Intelligente komponenter i
totalsystemer (hardware +
software)

Annen hardware:
– Autonome roboter
• Online bildefortolking
• Samarbeid
• Planleggingssystemer
• …
Hjernesimulering
• Kognisjonsvitenskap
• Selvorganiserende systemer
• …

Hva er “Kunstig intelligens” – 2
INFORMATIKK
STUDIET AV INTELLIGENTE
RELATERT
REALISERING AV DATASYSTEMER SOM KAN
SYSTEMER
TIL KOMPUTASJONELLE
SIES Å OPPVISE INTELLIGENT ADFERD
- DVS . ' SMARTERE ' SYSTEMER
er delfelt av
PROSESSER
er koblet via empirisk vitenskapelig metode
har
vitenskapelig
perspektiv
har
teknologisk
perspektiv
KUNSTIG INTELLIGENS (AI)
bygger bl.a. på
har metoder
har metoder
MATEMATIKK
SYMBOLORIENTERTE METODER
(KUNNSKAPSBASERTE METODER)
FILOSOFI
KOGNITIV
PSYKOLOGI
BIOLOGI
A. Aamodt, NTNU-IDI
SUBSYMBOLSKE METODER
(BIO-INSPIRERTE METODER)
KUNNSKAPSBASERTE METODER
- UTVIKLINGSTRENDER
Heuristiske
regler
Regelbaserte systemer
A. Aamodt, NTNU-IDI
(f.eks.: MYCIN)
KUNNSKAPSBASERTE METODER
- UTVIKLINGSTRENDER
Kontroll-kunnskap
Heuristiske
regler
A. Aamodt, NTNU-IDI
Eksplisitt kontrollkunnskap
(f.eks. NEOMYCIN)
- kunnskap om typer regler for typer tilstander
KUNNSKAPSBASERTE METODER
- UTVIKLINGSTRENDER
Kontroll-kunnskap
Heuristiske
regler
Dyp
kunnskap
A. Aamodt, NTNU-IDI
Dypere modeller, lærebok-kunnskap
(f.eks. CASNET)
- flere relasjoner, semantiske nett, rammer
KUNNSKAPSBASERTE METODER
- UTVIKLINGSTRENDER
Kontroll-kunnskap
Heuristiske
regler
Spesifikke
case
Dyp kunnskap
Fra generell kunnskap til situasjons-spesifikke case
(f.eks. CYRUS, PROTOS)
- case-basert resonnering
A. Aamodt, NTNU-IDI
The Case-Based Reasoning (CBR) Cycle
(Aamodt&Plaza 1994)
A. Aamodt, NTNU-IDI
KUNNSKAPSBASERTE METODER
- UTVIKLINGSTRENDER
Kontroll-kunnskap
Heuristiske
regler
Spesifikke
case
Dyp kunnskap
Integrerte systemer
(f.eks. SOAR, CREEK, META-AQUA)
- totalarkitekturer for intelligent problemløsning
A. Aamodt, NTNU-IDI
Herb Simon
A. Aamodt, NTNU-IDI
A. Aamodt, NTNU-IDI
A. Aamodt, NTNU-IDI
A. Aamodt, NTNU-IDI
Subsymbolic / Bio-inspired AI Methods
A. Aamodt, NTNU-IDI
Emergence
• The signal feature of life is not the carbon-based substrate...(but)...that the
local dynamics of a set of interacting entities (e.g. molecules, cells, etc.)
supports an emergent set of global dynamical structures which stabilize
themselves by setting the boundary conditions within which the local
dynamics operates (Charles Taylor, biologist, UCLA)
A. Aamodt, NTNU-IDI
Swarm Intelligence
e  mc 2
z 2  x2  y 2

• Follow Trail
• Find Food
•Make Trail
A. Aamodt, NTNU-IDI
Termite Arch-Building (Stigmergy)
Turtles, Termites and Traffic Jams: Explorations
in Massively Parallel Microworlds (Resnick, 1994)
pheremone
A. Aamodt, NTNU-IDI
Columns to Arches
Positive Feedback:
Pheromone Concentration
in middle gets higher and higher
as more dirt balls are added.
A. Aamodt, NTNU-IDI
Boids (Craig Reynolds)
http://www.red3d.com/cwr/boids/
A. Aamodt, NTNU-IDI
Ubiquity of Emergence
A. Aamodt, NTNU-IDI
Emergence &
Intelligence
Emergence Spectrum
How does intelligent behavior
arise from the interactions of
100 billion neurons, without
central control?
How has the brain evolved?
A. Aamodt, NTNU-IDI
Evolutionary Progressions along the Intelligence
Spectrum
Sense & Act:
Reason:
Calculate:
Living organisms
Computers
10,000,000+ years.
15+ years
100,000+ years.
30+ years
1,000+ years 50+ years
• Evolution of reasoning was tightly constrained and influenced by
sensorimotor capabilities. Else extinction!
• GOFAI systems are often in their own little worlds, making unreasonable
assumptions about independent sensorimotor apparatus.
• To achieve AI’s scientific goal of understanding human intelligence, the road
from sense-and-act to reasoning via simulated evolution may be the only
way.
A. Aamodt, NTNU-IDI
Cognitive Incrementalism
• Tacit assumption of SEAI research.
• Cognition (and hence common sense) is an extension of
sensorimotor behavior.
• This is the idea that you do indeed get full-blown, human
cognition by gradually adding ’bells and whistles’ to basic
(embodied, embedded) strategies of relating to the present at
hand…Mindware, pg. 135 (Andy Clark, 2001).
• I am, therefore I think.
• Brooks, Steels, Pfeifer, Scheier, Beer, Thelens, Nolfi,
Floreano…
A. Aamodt, NTNU-IDI
Darwinian Evolution
Physiological, Behavioral
Phenotypes
Natural Selection
Ptypes
Reproduction
Sex
Morphogenesis
Genotypes
Recombination
& Mutation
Genetic
A. Aamodt, NTNU-IDI
Gtypes
Evolutionary Algorithms
Parameters,
Code,
Neural Nets,
Rules
Semantic
Performance Test
P,C,N,R
R &M
Translate
Generate
Bit Strings
Syntactic
A. Aamodt, NTNU-IDI
Recombination
& Mutation
Bits
Artificial Neural Networks
A. Aamodt, NTNU-IDI
GOFAI
World
Model
Behav
Gen
World
Body
Brain
Connectionism
World
Model
Behav
Gen
World
Body
SEAI
The world is its own best model… Rodney Brooks
World
Model
Behav
Gen
Brain
A. Aamodt, NTNU-IDI
Body
World
GOFAI -vs- SEAI
Brittle Nerds -vs- Well-Rounded Insects
Selection
Pressure
Knowledge
GOFAI
SEAI
Knowledge Cramming
-vsAdaptive Systems
A. Aamodt, NTNU-IDI
A master thesis in AI at IDI
– a few examples
A. Aamodt, NTNU-IDI
IDIs Seksjon for Intelligente Systemer
- Organisering i 3 faggrupper
• Kunnskapsbaserte systemer
–
–
–
–
–
Case-basert resonnering
Kunnskapsmodellering
Intelligente agenter
Adaptive brukergrensesnitt
Usikkerhetsbehandling/grafiske
modeller
– Bildebehandling/kunstig syn
– Maskinlæring/datamining.
• Selvorganiserende systemer
–
–
–
–
–
A. Aamodt, NTNU-IDI
Evolusjonære metoder
Konneksjonisme
Nevrovitenskap
Kunstig liv
Maskinlæring
• Språkteknologi
– Naturlig språklig fortåelse
– Beregnbar logikk
– Tekstmining
– BusTuc
• 31 ansatte:
–
–
–
–
11 heltidsstillinger
4 Deltid
3 Forskere
13 PhD studenter
• 20 – 25 MSc studenter per år
Eksempler på master-oppgaver
Improved game AI through case-based and statistical reasoning
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Bilde- og/eller Video-analyse
(Her: Segmentere bilder av karbonfiberarmert epoxy)
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Bilde- og/eller Video-analyse
(Her: Segmentere bilder av fisk i Mauritius)
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Robots (pictured) that
interact with either a real
or simulated other robot.
Within our PUCKER
system, researchers and
students can easily test
their AI control strategies
on this type of robot (epucks).
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Intelligent Hardware
Today’s hardware technologies, especially Field programmable
Gate Arrays (FPGAs), provide many possibilities for the
creation of intelligent Hardware - that is AI techniques
embedded in hardware.
Such embedding may be for the purpose of speed-up of a given AI
technique for perhaps real-time application requirements or for
the purpose of creating hardware circuits, applying bioinspired techniques as the design technique.
The latter is known as the field of Evolvable Hardware and
includes applications in today’s technology and approaches to
achieve computation in tomorrow’s technology. Application
areas range from Vision, art to electronic circuits.
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Språkteknologi - maskinoversetting
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Textual CBR.
Discovery of causal relations in incident reports
•
An incident report (i.e., a 'textual case') describes how a problem unfolds. That is, the story
starts with less important 'symptoms'/evidence which, in turn, triggers/causes more serious
ones, and this chain of evidence ends up with an undesired, anomalous event. It is
important to identify the events when they are small, and discover the causal mechanisms
underlying the chain of events.
•
Use of eye-tracking in the selection of important features in a text and determining how
important they are - the latter is called 'weighting’. This in cooperation with people at
Dragvoll.
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Computer Assisted Assessment
and Treatment of Pain
Probabilistic networks, Rules, CBR,
meta-level reasoning
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Data mining and Decision support in Fish Farming
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Evolving Populations of
Social Insects to Perform
Annular Sorting
Vegard Hartmann
Acting
Sensing
A. Aamodt, NTNU-IDI
P = Pick up
F = Forward
L = Left
D = Deposit
B = Backward
R = Right
Andre Hei Vik
Eksempler på master-oppgaver
Fitness
Evaluation
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Three-object annular structure
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Reducing unwanted downtime in oil drilling
• One day of unwanted downtime on this rig
means increased cost of 1,6 MNOK for the
ongoing drilling operation.
• Providing the relevant experience and
getting the right information precisely
when needed will reduce unwanted
operational downtime.
• The result is a more reliable drilling
process, reduced drilling costs, and
increased productivity.
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
Improved decision support
through experience capture
and reuse
- pattern analysis
- case-based reasoning
A. Aamodt, NTNU-IDI
Eksempler på master-oppgaver
A. Aamodt, NTNU-IDI
DIS har deltatt i etablering av tre
spin-off selskaper:
- LingIT AS
- naturlig språk tolkning og dialogsystemer
- Trollhetta AS
- bildeanalyse og beslutningsstøtte
- Verdande Technology AS
- erfarings-lagring og aktiv gjenbruk,
primært innen oljeboring
A. Aamodt, NTNU-IDI
AI
- covers a lot of methods and application areas
- is interesting, useful, and fun
So, learn your
- basic AI formalisms, such as
- logics
- representations
- state-space search methods
Link to videos shown (and more!):
http://videolectures.net/aaai07/
http://videolectures.net/aaai08/
http://videolectures.net/ijcai09_video_competition/
A useful link to all of AI: http://www.aaai.org/aitopics
A. Aamodt, NTNU-IDI
A. Aamodt, NTNU-IDI
Evolutionary Computation
A. Aamodt, NTNU-IDI
Related documents
8.7 Artificial Intelligence
8.7 Artificial Intelligence
Demens - Sykehuset Innlandet HF
Demens - Sykehuset Innlandet HF