1 / 69

IAI REVISION 2012

IAI REVISION 2012. Turing Test. Turing (1950) “Computing machinery and intelligence": Can machines think? Can machines behave intelligently? Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes

asabi
Download Presentation

IAI REVISION 2012

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. IAI REVISION 2012

  2. Turing Test Turing (1950) “Computing machinery and intelligence": Can machines think? Can machines behave intelligently? Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes Suggested major components of AI: knowledge, reasoning, language understanding, learning Problems: Turing test is not reproducible, constructive, or amenable to mathematical analysis

  3. AI is not trying to copy humans • “artificial flight” was successful because the Wright brothers stopped mimicking birds. • We don’t want to copy pigeons. • Where else is the idea of a “gliding wing” and a propeller used in nature?

  4. Laws of Thought “Socrates is a man; all men are mortal; therefore Socrates is mortal.” LOGIC In 1965 computer programs existed that could in principle solve any solvable problem described in logical notation (however if no solution exists, the program would not terminate). How to we formally state real-world problems. Some problems take too long to solve exactly.

  5. Economics • How do we make decisions to maximize payoff (utility, money, happiness). • How do we do this when others cooperate or do not cooperate (criminals). • What about if the reward is not immediate, but maybe delayed far into the future. • Decision theory/game theory/operations research.

  6. History of AI McCulloch and Pitts (1943) on/off perceptron. Hebb (1949) Hebbian learning rule. Turing (1950) “Computing Machinery and Intelligence” Newell and Simon (1976) physical symbol system hypothesis Samuel (1952) checkers player; the program leaned to play better than its creator I CAN TELL YOU HOW IN THE DISCUSSION THIS AFTERNOON

  7. Game playing • IBM’s Deep Blue defeated the world champion Garry Kasparov. • “a new kind of intelligence” • IBM’s stock increased by $18 billion USD. • By studying this, chess players could draw!!! • Recently the computer is much better. • But what about “GO”, or other games?

  8. Vacuum-Cleaner • Vacuum agent perceives • which square (A or B) • and if clean or dirty. • It has actions; move left/right, suck, do nothing. • One simple function; if current square dirty, then suck, else move to other square. • We can write perceived state and action pairs • [A, Clean] right (if in A && clean, then move right) • [A, Dirty] suck (if in A && dirty, then suck)

  9. States and Actions • A state is a description of the world now. • An action is a transition from one state to another. • Not exactly the same but in java – instance variables are like state e.g. person = {name, age} • An action (java Method) changes the state with get/set methods.

  10. Formulation of Problem Domain • State: [l, c, d] robot=left, left room is clean, right room is dirty. Or in Binary [0,1,0] • Initial state:[l, d, d] • Action: move Left/right, suck. • Transition diagram: next slide • Goal states: {[l, c, c], [r, c, c]} • Path cost: number of actions (maybe sucking takes twice as much energy as moving??)

  11. State transition diagram for vacuum cleaner world. Note – some actions Are reversible and some Are not - which?

  12. 2.3.2 Properties of task environment • Fully observable vs. partially observable. • Single agent vs. multiple agent. (competitive vs. cooperative) • Deterministic vs. stochastic. • Episodic vs. sequential. • Discrete vs. continuous. • Known vs. unknown.

  13. 2.4.2 simple reflex agents IF condition THEH action. Human reflexes e.g. blinking, knee jerk. A fly avoid getting squatted by a human Other examples.

  14. 2.4.3 model-based reflex agents Example; we gasp for breath, even under water. A fly will move if we try to swat it. BLUSHING.

  15. 2.4.4 goal-based • There is a desirable goal state of the world. • goal egcrossing a road. • Children and orange juice in tall/short glass

  16. 2.4.6 general learning agent. Instead of writing thecomponents ourselves, why not let the machine learn? Turing (1950). http://www.youtube.com/watch?v=lrYPm6DD44M&feature=relmfu http://www.youtube.com/watch?v=BGPGknpq3e0

  17. Search UNIFORMED SEARCH • Depth first and breath first search. • Uniform cost search (expands the cheapest cost – how far travelled so far). h(n) INFORMED SEARCH • Greedy (expand first closest to goal according to some information). Funciton g(n) • A* (A star) f(n)= h(n)+g(n)

  18. Differences in Search methods • All of them work the same way!!! • The only difference is the order in which they sort the list • Depth first – FIFO, breath first FILO • Greedy g(n), uniform f(n), A* f(n)+g(n) • Uniformed search – looks in all directions (no knowledge of where the goal is) • Informed search – is directed toward the goal by information e.g. straight line distance to goal city.

  19. Map of Romania

  20. Breath First Search

  21. Depth First Search

  22. Greedy Search

  23. A *search • Expand cheapest according to distance travelled so far + expected distance to travel.

  24. Resolution - summary If we know (knowledge base) • A or B • Not B Then we can conclude (the knowledge base resolves to) • A The propositions must be in CNF (conjunctive normal form). We add the negation of what we want to prove. If we get a contradiction (false), then the theorem/proposition is true. (this is called proof by contraditction. )

  25. Resolution Algorithm Small example Is it sunny? sunny = TRUE? Prove sunny Knowledge base: sunny daytime sunny V night

  26. Resolution Algorithm Small example Is it sunny? sunny = TRUE? Prove sunny Knowledge base: sunny daytime sunny V night ¬sunny Negate it Add it to the knowledge base CONTRADICTION ¬sunny = FALSE Therefore: sunny = TRUE

  27. Procedure for converting to CNF • (a) To eliminate ↔, • (a ↔ b) ≡ (a → b) Λ(b→ a) • (b) To eliminate →, • (a → b) ≡ ¬ a ν b • (c) Double negation ¬ (¬a) ≡ a • (d) De Morgan • ¬ (a Λ b) ≡(¬a ν¬b) ¬(a ν b) ≡(¬a Λ¬b) • (e) Distributivity of Λover ν • (a Λ(b ν c )) ≡((aΛ b) ν (a Λ c)) • (f) Distributivity of νover Λ • (a ν(b Λ c )) ≡((a ν b) Λ(a ν c))

  28. Two player games

  29. MinMax

  30. Alpha beta pruning • Pruning – means cutting off redundant parts • Typically we “prune a tree” • MinMax considers all possibelities, however, using

  31. α-β pruning example

  32. α-β pruning example

  33. α-β pruning example

  34. α-β pruning example

  35. α-β pruning example

  36. Learning By Example • Perceptrons (single layer) – linearly seperable data. • Artificial Neural Networks (multilayer perceptrons – usually 2 or 3) • Support Vector Machines – linearly separable data. • Project/transform into higher dimensional space e.g. 2D to 3D and re-represent – then apply a Support Vector Machine.

  37. The First Neural Networks It consisted of: A set of inputs - (dendrites) A set of weights – (synapses) A processing element - (neuron) A single output - (axon)

  38. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks The activation of a neuron is binary. That is, the neuron either fires (activation of one) or does not fire (activation of zero).

  39. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks θ = threshold Output function: If (input sum < Threshold) output 0 Else output 1

  40. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks Each neuron has a fixed threshold. If the net input into the neuron is greater than or equal to the threshold, the neuron fires

  41. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks Neurons in a McCulloch-Pitts network are connected by directed, weighted paths

  42. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks • If the weight on a path is positive the path is excitatory, otherwise it is inhibitory • x1 and x2 encourage the neuron to fire • x3 prevents the neuron from firing

  43. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks The threshold is set such that any non-zero inhibitory input will prevent the neuron from firing (This is only a rule for McCulloch-Pitts Networks!!)

  44. X1 X3 Y 2 X2 2 -1 McCulloch and Pitts Networks It takes one time step for a signal to pass over one connection.

  45. 1 1 ? 2 0 0.5 1.5 Worked Examples on Handout 1 Threshold Function: If input sum < Threshold return 0 Else return 1 Does this neuron fire? Does it output a 0 or a 1? Inputs • Multiply the inputs to the neuron by the weights on their paths • Add the inputs • Apply the threshold function 2 3.5 0 Threshold(θ) = 4 1.5 3.5 < 4 So neuron outputs 0

  46. Answers • Using McCulloch-Pitts model we can model some logic functions • In the exercise, you have been working on logic functions • AND • OR • NOT AND

  47. Answers AND Function X Threshold(θ) = 2 1 Z 1 Y Threshold Function: If input sum < Threshold return 0 Else return 1

  48. Answers OR Function X Threshold(θ) = 2 2 Z 2 Y Threshold Function: If input sum < Threshold return 0 Else return 1

  49. Answers (This one is not a McCulloch-Pitts Network) NOT AND (NAND) Function X Threshold(θ) = -1 -1 Z -1 Y Threshold Function: If input sum < Threshold return 0 Else return 1

  50. One additional example AND NOT Function X Threshold(θ) = 2 2 Z -1 Y Threshold Function: If input sum < Threshold return 0 Else return 1

More Related