Ce diaporama a bien été signalé.
Le téléchargement de votre SlideShare est en cours. ×

Introduction to Artificial Intelligence and few examples

Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Publicité
Prochain SlideShare
ARTIFICIAL INTELLIGENCE ppt.
ARTIFICIAL INTELLIGENCE ppt.
Chargement dans…3
×

Consultez-les par la suite

1 sur 31 Publicité

Plus De Contenu Connexe

Diaporamas pour vous (20)

Les utilisateurs ont également aimé (20)

Publicité

Similaire à Introduction to Artificial Intelligence and few examples (20)

Publicité

Plus récents (20)

Introduction to Artificial Intelligence and few examples

  1. 1. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 1
  2. 2. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 2
  3. 3. What is Human intelligence? •  It’s a composi?on of abili?es like Ravi Kumar B N, Asst.Prof,CSE,BMSIT 3 Learning Understanding of Language PerceivingReasoning Feeling
  4. 4. What is intelligence? •  The ability to learn or understand from experience •  The ability to acquire and retain knowledge •  The ability to respond quickly and successfully to a new situa?on •  The ability to use reason to solve problems If intelligence is learning, understanding, retaining, responding, and using reason then what is AI? Ravi Kumar B N, Asst.Prof,CSE,BMSIT 4
  5. 5. Quick Answer from Academia q  Modeling human cogni8on using computers. q  Study of making computers do things which at the moment people are beNer at.. q  Making computers do things which require intelligence. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 5
  6. 6. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 6 More Formal Definition of AI q AI is a branch of computer science which is concerned with the study and crea?on of computer systems that exhibit Some form of intelligence. Or Those characteris?cs which we associate with intelligence in human behavior. q It is the science and engineering of making intelligent machines, especially intelligent computer programs.
  7. 7. What’s Involved in Intelligence? q  Ability to interact with the real world Ø  To perceive, understand, and act •  e.g., speech recogni?on and understanding q  Searching the best solu?on - medical q  Reasoning and Planning Ø  Modeling the external world – delivery robot Ø  Solving new problems, planning, and making decisions Ø  Ability to deal with unexpected problems, uncertain?es q  Learning and Adapta?on Ø  We are con?nuously learning and adap?ng Ø  our internal models are always being “updated” •  e.g., a baby learning to categorize and recognize animals Ravi Kumar B N, Asst.Prof,CSE,BMSIT 7
  8. 8. John McCarthy •  (September 4, 1927 – October 24, 2011) was an American Computer Scien?st And Cogni?ve Scien?st. •  McCarthy was one of the founders of the discipline of Ar?ficial Intelligence. •  He coined the term "Ar?ficial Intelligence" (AI) Ravi Kumar B N, Asst.Prof,CSE,BMSIT 8
  9. 9. Two dimensions •  Thinking/Reasoning vs. Behavior/Ac?on. •  Success according to human standards vs. success according to an ideal concept of intelligence ( ra?onality ): Four Categories. ü  Systems that think like humans (focus on reasoning and human framework). ü  Systems that think ra?onally (focus on reasoning and a general concept of intelligence). ü  Systems that act like humans (focus on behavior and human framework). ü  Systems that act ra?onally (focus on behavior and a general concept of intelligence). Views of AI fall into four categories in Two dimensions: Ravi Kumar B N, Asst.Prof,CSE,BMSIT 9
  10. 10. Definition of AI Ravi Kumar B N, Asst.Prof,CSE,BMSIT 10 Systems that Think like Humans “The exciting new effort to make computers think…. Machine with minds,….” (Haugeland, 1985) “[The automation of] activities that we associated human thinking, activities such as decision –making, problem solving, learning…”(Bellman,1978) Systems that Think Rationally “The study of mental faculties through the use of computational models” (Charnaik and McDermott,1985) “The study of the computations that make it possible to perceive, reason and act” (Wintson, 1992) Systems that Act like Humans “The art of creating machines that perform functions that require intelligence when performed by people” (Kurzwell, 1990) “The study of how to make computers do things at which, at the moment, people are better” (Rich and Knight,1991) Systems that Act Rationally “A field of study that seeks to explain and emulate intelligent behavior in terms of computational processes” (Schalkoff,1990) “The branch of computer science that is concerned with the automation of intelligent behavior” (Luger and Stubble field)
  11. 11. Acting Humanly : Turing Test Ravi Kumar B N, Asst.Prof,CSE,BMSIT 11 Alan Turing Born: 23 JUN 1912, London Died: 17 JUN 1954 computer scien?st, mathema?cian, logician, cryptanalyst and theore?cal biologist. ¨ “Can Machine think?” -> “Can Machines behave intelligently” ¨ Opera?onal test for intelligent behavior: the Imita?on Game. ¨ The computer would need to possess the following capabili?es: •  Natural Language Processing •  Knowledge Representa<on •  Automated Reasoning •  Machine Learning
  12. 12. Place both a human and a machine mimicking human responses outside the field of direct observation and use an unbiased interface to interrogate them. If the responses are distinguishable, the machine is not displaying intelligence. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 12
  13. 13. Thinking Humanly q Cogni?ve Science approach -  Try to get “inside” our minds- Introspec?on- trying to catch our own thoughts as they go by and through psychological experiments. -  E.g.. Conduct experiments with people to try to “reverse-engineer” how we reason, learning, remember, predict. q Problems - Humans don’t behave ra?onally. -  The reverse engineering is very hard to do. -  The brain’s hardware is very different to a computer program. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 13
  14. 14. Thinking Rationally: The “laws of thought” approach q The Greek philosopher Aristotle was one of the first to aNempt to codify ``right thinking,'' that is, irrefutable reasoning processes. q He gave Syllogisms that always yielded correct conclusion when correct premises are given. q These laws of thought were supposed to govern the opera?on of the mind, and ini?ated the field of logic. q The logicist tradi?on in AI hopes to create intelligent systems using logic programming. q However there are two obstacles to this approach. Ø First, It is not easy to take informal knowledge and state in the formal terms required by logical nota?on, par?cularly when knowledge is not 100% certain. Ø Second, solving problem principally is different from doing it in prac?ce. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 14
  15. 15. Acting Rationally: The rational agent approach q What means “behave ra<onally” for a person/system: Ø Take the right/ best ac?on to achieve the goals, based on his/its knowledge and belief q Example. Assume I don’t like to get wet (my goal), so I bring an umbrella (my ac?on). Do I behave ra?onally? Ø The answer is dependent on my knowledge and belief Ø If I’ve heard the forecast for rain and I believe it, then bringing the umbrella is ra?onal. Ø If I’ve not heard the forecast for rain and I do not believe that it is going to rain, then bringing the umbrella is not ra?onal. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 15
  16. 16. The rational agent approach q An agent is en?ty that perceives its environment and is able to execute ac?ons to change it. q Agents have inherent goals that they want to achieve. q A Ra?onal agent acts in a way to maximize the achievement of its goals q True maximiza?ons of goals requires omniscience and unlimited computa?onal abili?es q Limited ra?onality involves maximizing goals within the computa?onal and other resources available. Ravi Kumar B N, Asst.Prof, CSE,BMSIT 16
  17. 17. History 1943  Mc Culloch & PiNs: Boolean circuit model of brain 1950  Turing’s “Compu?ng Machinery and Intelligence” 1950s Early AI programs, including Samuel’s checkers program, Newell & Simon’s Logic Theorist, Gelernter’s Geometry Engine. 1956 Dartmouth mee?ng : “Ar?ficial Intelligence” adopted 1965 Robinson’s complete algorithm for logical reasoning 1966-73 AI discovers computa?onal complexity Neural network research almost disappears 1969-79 Early development of knowledge-based systems 1980 AI becomes an industry 1986 Neural networks return to popularity 1987 AI becomes a science 1995 The emergence of intelligent agents Ravi Kumar B N, Asst.Prof,CSE,BMSIT 17
  18. 18. Applications of AI: q Natural Language Understanding q Expert Systems q Planning and Robo?cs q Machine Learning q Game Playing Ravi Kumar B N, Asst.Prof,CSE,BMSIT 18
  19. 19. Natural Language Processing q To design and build soqware that will analyze understand and generate languages that human use naturally. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 19
  20. 20. Modes of communication q Text based. q Dialogue based. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 20
  21. 21. Speech Recognition q Process of conver?ng sound signal captured by microphone or mobile/telephone to a set of words. q 70-100 words / min with accuracy of 90% Ravi Kumar B N, Asst.Prof,CSE,BMSIT 21
  22. 22. Computer Vision q Ability of a machine to extract informa?on from an image that is necessary to solve a task —  Image Acquisi?on —  Image Processing —  Image Analysis —  Image understanding Ravi Kumar B N, Asst.Prof,CSE,BMSIT 22
  23. 23. Intelligent Robot q Tend to mimic human sensing and decision making abili?es so that they can adopt themselves to certain condi?ons and modify their ac?ons. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 23
  24. 24. Expert Systems q These are Soqwares used for decision making . q Automated Reasoning and Theorem Proving. q Troubleshoo?ng Expert Systems. q Stock Market Expert System. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 24
  25. 25. Fields of AI q Computer science: —  Graphical User Interface —  Automa?c Storage management —  Object Oriented Programming —  Data miming —  computer gaming q Telecommunica?on: •  Automated Online Assistants •  Voice dialing •  Speech Recogni?on Ravi Kumar B N, Asst.Prof,CSE,BMSIT 25
  26. 26. Fields of AI Avia?on & Automa?on: •  NASA's fight research center. •  Voice recogni?on in fighter jets. •  Direc?ons to A.I pilots through air traffic controllers. •  Automa?c Gearing System in Cars. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 26
  27. 27. Fields of AI Robo?cs: •  Assembling Robots •  Welding Robots •  Behavior based robo?cs •  Dancing Robots •  Robot naviga?on Ravi Kumar B N, Asst.Prof,CSE,BMSIT 27
  28. 28. Daily life applications •  Home Security •  Bank •  Post office •  Websites •  Digital cameras •  News and publishing •  Financial trades •  Health and medicine •  Games and toys Ravi Kumar B N, Asst.Prof,CSE,BMSIT 28
  29. 29. How AI is different???????? Ravi Kumar B N, Asst.Prof,CSE,BMSIT 29 Ar?ficial Intelligence Non Crea?ve Precise Consistency Mul?tasking Natural Intelligence Crea?ve May Contain Error Non Consistent Can’t Handle
  30. 30. Drawbacks of A.I •  Limited Ability •  Slow Real Time Response •  Can’t Handle Emergency Situa?on •  Difficult code •  High Cost Ravi Kumar B N, Asst.Prof,CSE,BMSIT 30
  31. 31. Ravi Kumar B N, Asst.Prof,CSE,BMSIT 31 Many Hollywood movies come with the future technology, that technology we can see in our future. Have a look some of them…. In this movie people to purchase remote controlled humanoid robots through which they interact with society. These fit, attractive, remotely controlled robots ultimately assume their life roles, enabling people to experience life vicariously from the comfort and safety of their own homes. Alex (Robocop) at first rejects his current condition upon seeing that his original body now consists of only lungs, throat, head and right hand when the armor and Cybernetic components are fully removed, but he is convinced by Norton to be strong for his wife and son. He had loose his body parts in a car bomb blast. Alex has him outfitted with the cybernetic body and software.

×