1 / 53

Snapshots of AI methods and applications

Snapshots of AI methods and applications. Agnar Aamodt and Keith Downing. Institutt for datateknikk og informasjonsvitenskap Seksjon for Intelligente Systemer NTNU. Hva er “Kunstig intelligens” – 1. “AI = Things that make you go WOW!” eller…??

omana
Download Presentation

Snapshots of AI methods and applications

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Snapshots of AI methods and applications Agnar Aamodt and Keith Downing Institutt for datateknikk og informasjonsvitenskap Seksjon for Intelligente Systemer NTNU

  2. 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”

  3. Example applications • Embedded systems • Intelligente komponenter i totalsystemer (hardware + software) • Annen hardware: • Autonome roboter • Online bildefortolking • Samarbeid • Planleggingssystemer • … • Hjernesimulering • Kognisjonsvitenskap • Selvorganiserende systemer • … • Software: • Pro-aktive beslutningsstøtte-systemer • Automatisk data-analyse • Lærende systemer, f.eks.: • Anbefalingssystemer • AI i spill • Ansiktsgjenkjenning • Naturlig språk • Robotnavigering, syn, planlegging • Adapterende GUI • ...

  4. REALISERING AV SOM KAN DATASYSTEMER STUDIET AV INTELLIGENTE SYSTEMER RELATERT TIL KOMPUTASJONELLE SIES Å OPPVISE INTELLIGENT ADFERD - . ' ' PROSESSER DVS SMARTERE SYSTEMER har er koblet via empirisk vitenskapelig metode har teknologisk vitenskapelig perspektiv perspektiv bygger bl.a. på MATEMATIKK METODER SYMBOLORIENTERTE (KUNNSKAPSBASERTE METODER) FILOSOFI KOGNITIV PSYKOLOGI SUBSYMBOLSKE (BIO-INSPIRERTE METODER) METODER BIOLOGI Hva er “Kunstig intelligens” – 2 INFORMATIKK er delfelt av KUNSTIG INTELLIGENS (AI) har metoder har metoder

  5. KUNNSKAPSBASERTE METODER - UTVIKLINGSTRENDER Heuristiske regler Regelbaserte systemer (f.eks.: MYCIN)

  6. KUNNSKAPSBASERTE METODER - UTVIKLINGSTRENDER Kontroll-kunnskap Heuristiske regler Eksplisitt kontrollkunnskap (f.eks. NEOMYCIN) - kunnskap om typer regler for typer tilstander

  7. KUNNSKAPSBASERTE METODER - UTVIKLINGSTRENDER Kontroll-kunnskap Heuristiske regler Dyp kunnskap Dypere modeller, lærebok-kunnskap (f.eks. CASNET) - flere relasjoner, semantiske nett, rammer

  8. KUNNSKAPSBASERTE METODER - UTVIKLINGSTRENDER Kontroll-kunnskap Heuristiske Spesifikke regler case Dyp kunnskap Fra generell kunnskap til situasjons-spesifikke case (f.eks. CYRUS, PROTOS) - case-basert resonnering

  9. The Case-Based Reasoning (CBR) Cycle (Aamodt&Plaza 1994)

  10. KUNNSKAPSBASERTE METODER - UTVIKLINGSTRENDER Kontroll-kunnskap Heuristiske Spesifikke regler case Dyp kunnskap Integrerte systemer (f.eks. SOAR, CREEK, META-AQUA) - totalarkitekturer for intelligent problemløsning

  11. VIDEO CLIP Herb Simon

  12. VIDEO CLIP

  13. Subsymbolic / Bio-inspired AI Methods

  14. 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 emergentset of global dynamical structures which stabilizethemselves by setting the boundary conditions within which the local dynamics operates (Charles Taylor, biologist, UCLA) Emergence

  15. Swarm Intelligence • Follow Trail • Find Food • Make Trail

  16. Termite Arch-Building (Stigmergy) Turtles, Termites and Traffic Jams: Explorations in Massively Parallel Microworlds (Resnick, 1994) pheremone

  17. Columns to Arches Positive Feedback: Pheromone Concentration in middle gets higher and higher as more dirt balls are added.

  18. Boids (Craig Reynolds) http://www.red3d.com/cwr/boids/

  19. Ubiquity of Emergence

  20. Emergence & Intelligence • Emergence Spectrum • How does intelligent behavior arise from the interactions of 100 billion neurons, without central control? • How has the brain evolved?

  21. Living organismsComputers Sense & Act: 10,000,000+ years. 15+ years Reason: 100,000+ years. 30+ years Calculate: 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. Evolutionary Progressions along the Intelligence Spectrum

  22. 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… Cognitive Incrementalism

  23. Sex Recombination & Mutation Morphogenesis Darwinian Evolution Physiological, Behavioral Phenotypes Natural Selection Ptypes Reproduction Gtypes Genotypes Genetic

  24. R &M Translate Recombination & Mutation Evolutionary Algorithms Semantic Parameters, Code, Neural Nets, Rules Performance Test P,C,N,R Generate Bits Bit Strings Syntactic

  25. Artificial Neural Networks

  26. World Model GOFAI Behav Gen Body World Brain Connectionism Behav Gen World Model Body World SEAI World The world is its own best model… Rodney Brooks Behav Gen Body World Model Brain

  27. GOFAI -vs- SEAI Brittle Nerds -vs- Well-Rounded Insects Selection Pressure Knowledge GOFAI SEAI Knowledge Cramming -vs- Adaptive Systems

  28. A master thesis in AI at IDI • a few examples

  29. 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 • 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

  30. Eksempler på master-oppgaver Improved game AI through case-based and statistical reasoning

  31. Eksempler på master-oppgaver

  32. Eksempler på master-oppgaver

  33. Eksempler på master-oppgaver Bilde- og/eller Video-analyse (Her: Segmentere bilder av karbonfiberarmert epoxy)

  34. Eksempler på master-oppgaver Bilde- og/eller Video-analyse (Her: Segmentere bilder av fiski Mauritius)

  35. 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 (e-pucks).

  36. 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 bio-inspired 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.

  37. Eksempler på master-oppgaver Språkteknologi - maskinoversetting

  38. Eksempler på master-oppgaver

  39. 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. Eksempler på master-oppgaver Textual CBR.

  40. Eksempler på master-oppgaver Computer Assisted Assessmentand Treatment of Pain Probabilistic networks, Rules, CBR, meta-level reasoning

  41. Eksempler på master-oppgaver Data mining and Decision support in Fish Farming

  42. Eksempler på master-oppgaver Evolving Populations ofSocial Insects to PerformAnnular Sorting Andre Hei Vik Vegard Hartmann P = Pick up D = Deposit F = Forward B = Backward L = Left R = Right Acting Sensing

  43. Eksempler på master-oppgaver Fitness Evaluation

  44. Eksempler på master-oppgaver Three-object annular structure

  45. 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. Eksempler på master-oppgaver Reducing unwanted downtime in oil drilling

  46. Eksempler på master-oppgaver Improved decision support through experience capture and reuse - pattern analysis - case-based reasoning

  47. Eksempler på master-oppgaver VIDEO CLIP

  48. 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

More Related