Artificial Intelligent introduction or history
- 2. In This Lecture: • What is intelligence? What is artificial intelligence? • Brief introduction of Artificial Intelligence • A very brief history of AI • AI in practice
- 3. What is Intelligence? • Intelligence: “the capacity to learn and solve problems” • in particular, the ability to solve novel problems • the ability to act rationally • the ability to act like humans
- 4. Artificial Intelligence • Artificial intelligence is that branch of science which makes machines perform tasks which would require intelligence when performed by humans (Marvin Minsky) • It is the science and engineering of making intelligent machines, especially intelligent computer programs.
- 5. Academics Disciplines relevant in AI • Philosophy Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality. • Mathematics Formal representation and proof, algorithms, computation, (un)decidability, (in)tractability • Probability/Statistics modeling uncertainty, learning from data • Economics utility, decision theory, rational economic agents • Neuroscience neurons as information processing units. • Psychology/ how do people behave, perceive, process cognitive Cognitive Science information, represent knowledge. • Computer building fast computers engineering • Control theory design systems that maximize an objective function over time • Linguistics knowledge representation, grammars
- 6. History of AI • 1943: early beginnings – McCulloch & Pitts: Boolean circuit model of brain • 1950: Turing – Turing's "Computing Machinery and Intelligence“ • 1956: birth of AI – Dartmouth meeting: "Artificial Intelligence“ name adopted • 1950s: initial promise – Early AI programs, including – Samuel's checkers program – Newell & Simon's Logic Theorist • 1955-65: “great enthusiasm” – Newell and Simon: GPS, general problem solver – Gelertner: Geometry Theorem Prover – McCarthy: invention of LISP
- 7. History of AI • 1966—73: Reality dawns – Realization that many AI problems are intractable – Limitations of existing neural network methods identified • Neural network research almost disappears • 1969—85: Adding domain knowledge – Development of knowledge-based systems – Success of rule-based expert systems, • E.g., DENDRAL, MYCIN • But were brittle and did not scale well in practice • 1986-- Rise of machine learning – Neural networks return to popularity – Major advances in machine learning algorithms and applications • 1990-- Role of uncertainty – Bayesian networks as a knowledge representation framework • 1995-- AI as Science – Integration of learning, reasoning, knowledge representation – AI methods used in vision, language, data mining, etc
- 8. Properties of Intelligent System • Ability to interact with the real world – to perceive, understand, and act – e.g., speech recognition and understanding – e.g., image understanding – e.g., ability to take actions, have an effect • Reasoning and Planning – modeling the external world, given input – solving new problems, planning, and making decisions – ability to deal with unexpected problems, uncertainties • Learning and Adaptation – we are continuously learning and adapting – our internal models are always being “updated” • e.g., a baby learning to categorize and recognize animals
- 9. More About Artificial Intelligence • Actually definitions of artificial intelligence can be grouped in 4 main categories
- 10. More About Artificial Intelligence • The previously mentioned categories of definitions can be considered along 2 dimensions:
- 11. More About Artificial Intelligence • The other dimensions can be the following
- 12. Explaining Definition SYSTEMS THAT THINK LIKE HUMANS • If we want to develop a computer that thinks like humans we need to know how people think. • Cognitive science integrates computational models developed in the area of artificial intelligence with techniques from psychology in order to develop theories about how the human mental mind works
- 13. Explaining Definition SYSTEMS THAT THINK RATIONALLY • This approach is related to logics, that is, logical rules make the mental mind of humans For example, if we know that All people have a head and Alex is one of people, than we can conclude that Alex has a head.
- 14. Explaining Definition SYSTEMS THAT ACT LIKE HUMANS - In this approach computer capabilities are compared with human capabilities - For this purpose a special test of intelligent behavior is defined. The test is called the Turing test.
- 15. Turing Test • The idea of the test is the following. There are 3 rooms. In the first one there is an artificial intelligence, in the second room- a person or natural intelligence, and in the third room there is a tester. The tester asks questions to both intelligences. If it is impossible to determine which answers were given by the person and which ones by the machine, than the machine has intelligence.
- 16. Explaining Definition SYSTEMS THAT ACT LIKE HUMANS To pass the Turing test the computer must have the following capabilities: • Natural language processing • Knowledge representation • Automated reasoning • Machine learning
- 17. How much Intelligent System We Can Build? • Chess Playing is a classic AI problem – well-defined problem – very complex: difficult for humans to play well
- 18. Golden Pearl 1 • DO NOT BEG FOR LITTLE THINGS OTHERWISE IT WILL BECOME YOUR HABIT