artificial intelligence
play

Artificial Intelligence (Sistemas Inteligentes) Pedro Cabalar - PowerPoint PPT Presentation

Artificial Intelligence (Sistemas Inteligentes) Pedro Cabalar Depto. Computacin Universidade da Corua, SPAIN Chapter 1. Introduction Pedro Cabalar (UDC) ( Depto. Computacin Universidade da Corua, SPAIN ) AI Chapter 1. Introduction


  1. Artificial Intelligence (Sistemas Inteligentes) Pedro Cabalar Depto. Computación Universidade da Coruña, SPAIN Chapter 1. Introduction Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 1 / 13

  2. Outline A definition of AI 1 Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 2 / 13

  3. A definition of AI A definition of AI 1 Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 3 / 13

  4. A definition of AI A bit of debate: what is AI? Take 5 min. to tell what Artificial Intelligence (AI) is all about. . . Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 4 / 13

  5. A definition of AI A bit of debate: what is AI? Take 5 min. to tell what Artificial Intelligence (AI) is all about. . . Debate: half class will be defenders and half class attackers. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 4 / 13

  6. A definition of AI A bit of debate: what is AI? Take 5 min. to tell what Artificial Intelligence (AI) is all about. . . Debate: half class will be defenders and half class attackers. What is AI? It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable. John McCarthy http://www-formal.stanford.edu/jmc/whatisai/ node1.html Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 4 / 13

  7. A definition of AI A bit of debate: what is AI? What do you think? Give arguments why AI is a . . . science 1 engineering 2 a constant disappointment 3 Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 5 / 13

  8. A definition of AI What is AI? A keypoint: what is intelligence? Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 6 / 13

  9. A definition of AI What is AI? A keypoint: what is intelligence? A definition will depend on human intelligence and we ignore many of its mechanisms. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 6 / 13

  10. A definition of AI What is AI? A keypoint: what is intelligence? A definition will depend on human intelligence and we ignore many of its mechanisms. The perception of intelligent behavior has changed along History. Example: a calculator looked intelligent a hundred years ago while some wouldn’t say a chess program looks intelligent today. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 6 / 13

  11. A definition of AI What is AI? A keypoint: what is intelligence? A definition will depend on human intelligence and we ignore many of its mechanisms. The perception of intelligent behavior has changed along History. Example: a calculator looked intelligent a hundred years ago while some wouldn’t say a chess program looks intelligent today. Many definitions of AI have been made. They can be classified as follows: Imitating human behavior: thinking like humans vs acting like humans Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 6 / 13

  12. A definition of AI What is AI? A keypoint: what is intelligence? A definition will depend on human intelligence and we ignore many of its mechanisms. The perception of intelligent behavior has changed along History. Example: a calculator looked intelligent a hundred years ago while some wouldn’t say a chess program looks intelligent today. Many definitions of AI have been made. They can be classified as follows: Imitating human behavior: thinking like humans vs acting like humans Focus on rational behaviour: thinking rationally vs acting rationally Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 6 / 13

  13. A definition of AI Acting humanly: the Turing test Alan Turing (1912 - 1954) The Turing test: we have two terminals A=controlled by a computer; B=with a human behind. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 7 / 13

  14. A definition of AI Acting humanly: the Turing test Alan Turing (1912 - 1954) The Turing test: we have two terminals A=controlled by a computer; B=with a human behind. C is a human interrogator that must find out who is who. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 7 / 13

  15. A definition of AI Acting humanly: the Turing test Alan Turing (1912 - 1954) The Turing test: we have two terminals A=controlled by a computer; B=with a human behind. C is a human interrogator that must find out who is who. We say A is intelligent = C cannot tell. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 7 / 13

  16. A definition of AI Acting humanly: the Turing test Can you imagine what A should be capable of? Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 8 / 13

  17. A definition of AI Acting humanly: the Turing test Can you imagine what A should be capable of? Natural language Knowledge representation Automated reasoning Machine learning Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 8 / 13

  18. A definition of AI Acting humanly: the Turing test Can you imagine what A should be capable of? Natural language Knowledge representation Automated reasoning Machine learning “Total” Turing test: includes video signal, perception and exchange of physical objects. . . Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 8 / 13

  19. A definition of AI Acting humanly: the Turing test Can you imagine what A should be capable of? Natural language Knowledge representation Automated reasoning Machine learning “Total” Turing test: includes video signal, perception and exchange of physical objects. . . Computer Vision Robotics Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 8 / 13

  20. A definition of AI Acting humanly: the Turing test Can you imagine what A should be capable of? Natural language Knowledge representation Automated reasoning Machine learning “Total” Turing test: includes video signal, perception and exchange of physical objects. . . Computer Vision Robotics These are the six main areas of AI and became the real goal, rather than the test itself. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 8 / 13

  21. A definition of AI Thinking humanly: Cognitive modeling Cognitive Science tries to join AI models with experimental techniques from Psychology to build (testable) theories about the human mind. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 9 / 13

  22. A definition of AI Thinking humanly: Cognitive modeling Cognitive Science tries to join AI models with experimental techniques from Psychology to build (testable) theories about the human mind. Two ways of tackling the problem of cognitive modeling: 1 Symbolic modeling: Use knowledge-based systems to capture abstract mental functions handling symbols. Marvin Minsky’s school. Marvin Minsky (1927-) Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 9 / 13

  23. A definition of AI Thinking humanly: Cognitive modeling Cognitive Science tries to join AI models with experimental techniques from Psychology to build (testable) theories about the human mind. Two ways of tackling the problem of cognitive modeling: 1 Symbolic modeling: Use knowledge-based systems to capture abstract mental functions handling symbols. Marvin Minsky’s school. Marvin Minsky (1927-) Subsymbolic modeling: try to follow the neural and associative 2 properties of the human brain using connectionst/neural network models. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 9 / 13

  24. A definition of AI Thinking humanly: Cognitive modeling Cognitive Science tries to join AI models with experimental techniques from Psychology to build (testable) theories about the human mind. Two ways of tackling the problem of cognitive modeling: 1 Symbolic modeling: Use knowledge-based systems to capture abstract mental functions handling symbols. Marvin Minsky’s school. Marvin Minsky (1927-) Subsymbolic modeling: try to follow the neural and associative 2 properties of the human brain using connectionst/neural network models. Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 9 / 13

  25. A definition of AI Thinking rationally: laws of thought Logicist tradition in AI. John McCarthy’s school. John McCarthy (1927-2011) Pedro Cabalar (UDC) ( Depto. Computación Universidade da Coruña, SPAIN ) AI Chapter 1. Introduction 10 / 13

Recommend


More recommend