1 / 51

Course Overview

Course Overview.  Done.  Done. What is AI? What are the Major Challenges? What are the Main Techniques? Where are we failing, and why? Step back and look at the Science Step back and look at the History of AI What are the Major Schools of Thought? What of the Future?. Course Overview.

ling
Télécharger la présentation

Course Overview

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. Course Overview Done Done • What is AI? • What are the Major Challenges? • What are the Main Techniques? • Where are we failing, and why? • Step back and look at the Science • Step back and look at the History of AI • What are the Major Schools of Thought? • What of the Future?

  2. Course Overview • What is AI? • What are the Major Challenges? • What are the Main Techniques? (How do we do it?) • Where are we failing, and why? • Step back and look at the Science • Step back and look at the History of AI • What are the Major Schools of Thought? • What of the Future?

  3. Course Overview • What is AI? • What are the Major Challenges? • What are the Main Techniques? (How do we do it?) • Where are we failing, and why? • Step back and look at the Science • Step back and look at the History of AI • What are the Major Schools of Thought? • What of the Future? • Search • Logics (knowledge representation and reasoning) • Planning • Bayesian belief networks • Neural networks • Evolutionary computation • Reinforcement learning

  4. Course Overview • What is AI? • What are the Major Challenges? • What are the Main Techniques? (How do we do it?) • Where are we failing, and why? • Step back and look at the Science • Step back and look at the History of AI • What are the Major Schools of Thought? • What of the Future? • Search • Logics (knowledge representation and reasoning) • Planning • Bayesian belief networks • Neural networks • Evolutionary computation • Reinforcement learning

  5. Course Overview • What is AI? • What are the Major Challenges? • What are the Main Techniques? (How do we do it?) • Where are we failing, and why? • Step back and look at the Science • Step back and look at the History of AI • What are the Major Schools of Thought? • What of the Future? • Search • Logics (knowledge representation and reasoning) • Planning • Bayesian belief networks • Neural networks • Evolutionary computation • Reinforcement learning These are all in fact types of “Machine Learning”

  6. Dealing with Uncertainty • The need to deal with uncertainty arose in “expert systems” • Code expertise into a computer systemExample: • Medical diagnosis: MYCIN • Equipment failure diagnosis in a factory • Sample from MYCIN: • IF • The infection is primary-bacteremia AND • The site of the culture is one of the sterile sites AND • The suspected portal of entry is the gastrointestinal tract • THEN • There is suggestive evidence (70%) that the infection is bacteroid • Expert systems often have long chains • IF X THEN Y … IF Y THEN Z … IF Z THEN W … • If uncertainty is not handled correctly, errors build up, wrong diagnosis • Also, there may be dependencies, e.g. X and Y depend on each other • Leads to more errors… • Need a proper way to deal with uncertainty

  7. How do Humans Deal with Uncertainty? • Not very well… • Consider a form of cancer which afflicts 0.8% of people (rare) • A lab has a test to detect the cancer • The test has a 98% chance to give an accurate result • Mr. Bloggs goes for the test • The result comes back positive • i.e. the test says he has cancer • What is the chance that he has the cancer? • 28% • Afflicts experts too • Studies have shown: human experts thinking of likelihoods do not reason like mathematical probability

  8. Metastatic cancer A Increased total serum count Brain Tumour B C Severe headaches D E Coma

  9. Metastatic cancer A No Link Increased total serum count Brain Tumour B C Severe headaches D E Coma

  10. Metastatic cancer A Increased total serum count Brain Tumour B C Severe headaches D E Coma

  11. Metastatic cancer A Increased total serum count Brain Tumour B C Severe headaches D E Coma

  12. Metastatic cancer A Increased total serum count Brain Tumour B C Severe headaches D E Coma

  13. Inference in Belief Networks • Questions for a belief network: • Diagnosis • Work backwards from some evidence to a hypothesis • Causality • Work forwards from some hypothesis to likely evidence • Test a hypothesis, find likely symptoms • In general – mixed mode • Give values for some evidence variables • Ask about values of others • No other approach handles all these modes • Reasoning can take some time • Need to be careful to design network • Local structure: few connections

  14. How Good are Belief Networks? • Relieves you from coding all possible dependencies • How many possibilities if full network? • Tools are available • Build network graphically • System handles mathematical probabilities • Case study: • Pathfinder a medical expert system • Assists pathologists with diagnosis of lymph-node diseases • Pathfinder is a pun • User enters initial findings • Pathfinder lists possible diseases • User can • Enter more findings • Ask pathfinder which findings would narrow possibilities • Pathfinder refines the diagnosis • Pathfinder version based on Belief Networks performs significantly better than human pathologists

  15. QUIZ

  16. “Machines will be capable, within _____ years, of doing any work that a man can do.” Herbert Simon, 1965.

  17. What disciplines are considered as sub-areas of Cognitive Science?

  18. 1966: “Any task that requires real understanding of natural language is too difficult for a computer” - Bar-Hillel

  19. Time flies like an arrow.

  20. Give an example which shows why speech recognition is hard for computers.

  21. Major tasks in robotics: • Localisation/mapping • Range finders • Landmarks • Always uncertainty • ?

  22. DARPA Grand Challenge 2004 150-mile route in Mojave Desert (off-road course)Best performance? (require accuracy to nearest 2 miles)

  23. Vision Hierarchy 4. High level Models 3. Mid level ???? 2. Putting together Multiple images 1. Low level processing on a single image 0. The physics of image formation

  24. Go (Wei Qi) • Humans don’t want to play computers because ?

  25. "Our ultimate objective is to make programs that learn from their experience as effectively as humans do. We shall…say that a program has common sense if ?” John McCarthy, "Programs with Common Sense", 1958.

  26. Defence A big user of AI. "... the deployment of a single ?????? called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year period." Tate A. Smart Planning. ARPI Proc. 1996.

  27. Can use logic to represent a hierarchy of concepts • isa(Tweety, canary) • isa(canary, bird) • isa(bird, animal) • isa(animal, living_thing) • isa(living_thing, physical_thing) • isa(physical_thing, tangible_thing) • isa(tangible_thing, thing) • What do we call this?

  28. “Machines will be capable, within _____ years, of doing any work that a man can do.” Herbert Simon, 1965.

  29. “Machines will be capable, within twenty years, of doing any work that a man can do.” Herbert Simon, 1965.

  30. What disciplines are considered as sub-areas of Cognitive Science?

  31. What disciplines are considered as sub-areas of Cognitive Science? • Cognitive Science • Psychology • Philosophy • Neuroscience • Artificial Intelligence • Linguistics • Anthropology

  32. 1966: “Any task that requires real understanding of natural language is too difficult for a computer” - Bar-Hillel

  33. 1966: “Any task that requires real understanding of natural language is too difficult for a computer” - Bar-Hillel

  34. Time flies like an arrow.

  35. Time flies like an arrow. • (You should) time flies as you would (time) an arrow • Time flies in the same way that an arrow would (time them) • Time those flies that are like arrows • Fruit flies like a banana • each of above • Time magazine travels straight when thrown

  36. Give an example which shows why speech recognition is hard for computers.

  37. Give an example which shows why speech recognition is hard for computers. • “eat I scream” vs. “eat ice cream”

  38. Major tasks in robotics: • Localisation/mapping • Range finders • Landmarks • Always uncertainty • ?

  39. Major tasks in robotics: • Localisation/mapping • Range finders • Landmarks • Always uncertainty • Motion planning • For body location in world • For arms/fingers

  40. DARPA Grand Challenge 2004 150-mile route in Mojave Desert (off-road course)Best performance? (require accuracy to nearest 2 miles)

  41. DARPA Grand Challenge 2004 150-mile route in Mojave Desert (off-road course)Best performance: 7.36 miles

  42. Vision Hierarchy 4. High level Models 3. Mid level ???? 2. Putting together Multiple images 1. Low level processing on a single image 0. The physics of image formation

  43. Vision Hierarchy 4. High level Models 3. Mid level Segmentation 2. Putting together Multiple images 1. Low level processing on a single image 0. The physics of image formation

  44. Go (Wei Qi) • Humans don’t want to play computers because ?

  45. Go (Wei Qi) • Humans don’t want to play computers because computers are too bad

  46. "Our ultimate objective is to make programs that learn from their experience as effectively as humans do. We shall…say that a program has common sense if ?” John McCarthy, "Programs with Common Sense", 1958.

  47. "Our ultimate objective is to make programs that learn from their experience as effectively as humans do. We shall…say that a program has common sense if it automatically deduces for itself a sufficient wide class of immediate consequences of anything it is told and what it already knows.” John McCarthy, "Programs with Common Sense", 1958.

  48. Defence A big user of AI. "... the deployment of a single ?????? called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year period." Tate A. Smart Planning. ARPI Proc. 1996.

  49. Defence A big user of AI. "... the deployment of a single logistics support aid called DART during the Desert Shield/Storm Campaign paid back all US government investment in AI/KBS research over a 30 year period." Tate A. Smart Planning. ARPI Proc. 1996.

  50. Can use logic to represent a hierarchy of concepts • isa(Tweety, canary) • isa(canary, bird) • isa(bird, animal) • isa(animal, living_thing) • isa(living_thing, physical_thing) • isa(physical_thing, tangible_thing) • isa(tangible_thing, thing) • What do we call this?

More Related