Artificial Intelligence. CSD 102 Introduction to Communication and Information Technologies Mehwish Fatima

Transcription

1 Artificial Intelligence CSD 102 Introduction to Communication and Information Technologies Mehwish Fatima

2 Objectives Division of labor Knowledge representation Recognition tasks Reasoning tasks Mehwish Fatima- CIIT Lahore 2

3 Thinking Machines Can you list the items in this picture? Mehwish Fatima- CIIT Lahore 3

4 Thinking Machines Can you count the distribution of letters in a book? Add a thousand 4-digit numbers? Match finger prints? Search a list of a million values for duplicates? Cover Image: Sergey Nivens/Shutterstock, Inc. Mehwish Fatima- CIIT Lahore 4

5 Thinking Machines Humans do best Can you list the items in this picture? Computers do best Can you count the distribution of letters in a book? Add a thousand4-digit numbers? Match finger prints? Search a list of a million values for duplicates? Mehwish Fatima- CIIT Lahore 5

6 Introduction Artificial intelligence (AI) Explores techniques for incorporating aspects of intelligence into computer systems The study of computer systems that attempt to model and apply the intelligence of the human mind For example, writing a program to pick out objects in a picture Mehwish Fatima- CIIT Lahore 6

7 Turing Test A test for intelligent behavior of machines Allows a human to interrogate two entities, both hidden from the interrogator A human A machine (a computer) If the interrogator is unable to determine which entity is the human and which the computer, the computer has passed the test. Mehwish Fatima- CIIT Lahore 7

8 Turing Test Artificial intelligence can be thought of as constructing computer models of human intelligence Weak equivalence Two systems (human and computer) are equivalent in results (output), but they do not arrive at those results in the same way Strong equivalence Two systems (human and computer) use the same internal processes to produce results Mehwish Fatima- CIIT Lahore 8

9 Turing Test Loebner prize The first formal instantiation of the Turing test, held annually Has it been won yet? Chatbots A program designed to carry on a conversation with a human user Mehwish Fatima- CIIT Lahore 9

10 A Division of Labor Categories of tasks Computational tasks Recognition tasks Reasoning tasks Computational tasks Tasks for which algorithmic solutions exist Computers are better (faster and more accurate) than humans Mehwish Fatima- CIIT Lahore 10

11 A Division of Labor (continued) Recognition tasks Sensory/recognition/motor skills tasks Humans are better than computers Reasoning tasks Require a large amount of knowledge Humans are far better than computers Mehwish Fatima- CIIT Lahore 11

12 Figure 14.2 Human and Computer Capabilities Mehwish Fatima- CIIT Lahore 12

13 Knowledge Representation Knowledge a body of facts or truths For a computer to make use of knowledge, it must be stored within the computer in some form Knowledge representation schemes Natural language Formal language Pictorial Graphical Mehwish Fatima- CIIT Lahore 13

14 Knowledge Representation (continued) Required characteristics of a knowledge representation scheme Adequacy Efficiency Extendability Appropriateness Mehwish Fatima- CIIT Lahore 14

15 How can we represent knowledge? We need to create a logical view of the data, based on how we want to process it Natural language is very descriptive, but does not lend itself to efficient processing Semantic networks and search trees are promising techniques for representing knowledge Mehwish Fatima- CIIT Lahore 15

16 A knowledge representation technique that focuses on the relationships between objects A directed graph is used to represent a semantic network or net Semantic Networks Mehwish Fatima- CIIT Lahore 16

17 Semantic Networks Network Design The objects in the network represent the objects in the real world that we are representing The relationships that we represent are based on the real world questions that we would like to ask That is, the types of relationships represented determine which questions are easily answered, which are more difficult to answer, and which cannot be answered Mehwish Fatima- CIIT Lahore 17

18 Semantic Networks Search Trees A structure that represents alternatives in adversarial situations such as game playing The paths down a search tree represent a series of decisions made by the players Mehwish Fatima- CIIT Lahore 18

19 Mehwish Fatima- CIIT Lahore 19

20 Recognition Tasks A neuron is a cell in the human brain, capable of: Receiving stimuli from other neurons through its dendrites Sending stimuli to other neurons through its axon Mehwish Fatima- CIIT Lahore 20

21 Recognition Tasks (continued) If the sum of activating and inhibiting stimuli received by a neuron equals or exceeds its threshold value, the neuron sends out its own signal Each neuron can be thought of as an extremely simple computational device with a single on/off output Human brain: a connectionist architecture A large number of simple processors with multiple interconnections Von Neumann architecture A small number (maybe only one) of very powerful processors with a limited number of interconnections between them Mehwish Fatima- CIIT Lahore 21

22 Recognition Tasks (continued) Artificial neural networks (neural networks) Simulate individual neurons in hardware Connect them in a massively parallel network of simple devices that act somewhat like biological neurons The effect of a neural network may be simulated in software on a sequential processing computer Mehwish Fatima- CIIT Lahore 22

23 Recognition Tasks (continued) Neural network Each neuron has a threshold value Incoming lines carry weights that represent stimuli The neuron fires when the sum of the incoming weights equals or exceeds its threshold value Both the knowledge representation and programming are stored as weights of the connections and thresholds of the neurons The network can learn from experience by modifying the weights on its connections Mehwish Fatima- CIIT Lahore 23

24 Reasoning Tasks Human reasoning requires the ability to draw on a large body of facts and past experience to come to a conclusion Artificial intelligence specialists try to get computers to emulate this characteristic Mehwish Fatima- CIIT Lahore 24

25 Intelligent Searching State space graph: After any one node has been searched, there are a huge number of next choices to try There is no algorithm to dictate the next choice State space search Finds a solution path through a state space graph Mehwish Fatima- CIIT Lahore 25

26 Intelligent Searching (continued) Each node represents a problem state Goal state: the state we are trying to reach Intelligent searching applies some heuristic (or an educated guess) to: Evaluate the differences between the present state and the goal state Move to a new state that minimizes those differences Mehwish Fatima- CIIT Lahore 26

27 Swarm Intelligence Swarm intelligence Models the behavior of a colony of ants Swarm intelligence model Uses simple agents that: Operate independently Can sense certain aspects of their environment Can change their environment May evolve and acquire additional capabilities over time Mehwish Fatima- CIIT Lahore 27

28 Intelligent Agents An intelligent agent: software that interacts collaboratively with a user Initially an intelligent agent simply follows user commands Over time Agent initiates communication, takes action, and performs tasks on its own using its knowledge of the user s needs and preferences Mehwish Fatima- CIIT Lahore 28

29 Expert Systems Rule based systems Also called expert systems or knowledge based systems Attempt to mimic the human ability to engage pertinent facts and combine them in a logical way to reach some conclusion A rule based system must contain A knowledge base: set of facts about subject matter An inference engine: mechanism for selecting relevant facts and for reasoning from them in a logical way Many rule based systems also contain An explanation facility: allows user to see assertions and rules used in arriving at a conclusion Mehwish Fatima- CIIT Lahore 29

30 Expert Systems (continued) A fact can be A simple assertion A rule: a statement of the form if... then... Modus ponens (method of assertion) The reasoning process used by the inference engine Inference engines can proceed through Forward chaining Backward chaining Forward chaining Begins with assertions and tries to match those assertions to if clauses of rules, thereby generating new assertions Mehwish Fatima- CIIT Lahore 30

31 Expert Systems (continued) Backward chaining Begins with a proposed conclusion Tries to match it with the then clauses of rules Then looks at the corresponding if clauses Tries to match those with assertions, or with the then clauses of other rules A rule based system is built through a process called knowledge engineering Builder of system acquires information for knowledge base from experts in the domain Mehwish Fatima- CIIT Lahore 31

32 The games we play In May 1997 world champion Garry Kasparov and the IBM chessplaying computer known as Deep Blue Kasparov utilizing recognition and reasoning, and Deep Blue churning out its high speed computations. In the final game, Kasparov lost the match by falling for a well known trap Mehwish Fatima- CIIT Lahore 32

33 Robotics Mobile robotics The study of robots that move relative to their environment, while exhibiting a degree of autonomy Sense plan act (SPA) paradigm The world of the robot is represented in a complex semantic net in which the sensors on the robot are used to capture the data to build up the net Mehwish Fatima- CIIT Lahore 33

34 Subsumption Architecture Rather than trying to model the entire world all the time, the robot is given a simple set of behaviors each associated with the part of the world necessary for that behavior Mehwish Fatima- CIIT Lahore 34

35 Sony's Aibo Robots Sojourner Rover Chris Willson/Alamy Courtesy of NASA/JPL-Caltech. Mehwish Fatima- CIIT Lahore 35

36 Spirit or Opportunity Rover Robots Area of applications with examples Video links Dw7rCuo mcutgqc Humanoid robots Video links: Asimohttps:// JlRPICfnmhw 6/24/national/science-health/humanoidrobot-exhibit-opens-tokyo/#.Vzjkw1R942x Mehwish Fatima- CIIT Lahore 36

37 Mehwish Fatima- CIIT Lahore 37

38 Other Applications of A.I Future of A.I How Robots work Reading Assignment Mehwish Fatima- CIIT Lahore 38