AI Chapter 01 - Artificial Intelligence PDF

Artificial Intelligence CSB2104 Prof. Abdel-Rahman Hedar Introduction Chapter 1 2  Contents » What is AI? » What tasks require AI? » How to achieve AI? » Branches of AI » AI Foundations » AI History 3 What is AI? 4 What is AI?...

Artificial Intelligence CSB2104 Prof. Abdel-Rahman Hedar Introduction Chapter 1 2  Contents » What is AI? » What tasks require AI? » How to achieve AI? » Branches of AI » AI Foundations » AI History 3 What is AI? 4 What is AI? Thinkin Thinkin g g Humanl Rationa y lly Acting Acting Humanl Rationa y lly 5  Acting Humanly: The Turing Test » Alan Turing's 1950 article Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent. » “Can machines think?”  “Can machines behave intelligently?” » The Turing test (The Imitation Game): Operational definition of intelligence. » Computer needs: Natural language processing, Knowledge representation, Automated reasoning, and Machine learning 6 Other AI Perspectives Thinking Humanly: Cognitive Science Thinking Rationally: Laws of Thought Acting Rationally: The Rational Agent 7 AI AI is the science and engineering of making intelligent machines which can perform tasks that require intelligence when performed by humans … 8 What tasks require AI? 9  Tasks that require AI » Solving a differential equation » Brain surgery » Inventing stuff » Playing Wheel of Fortune » What about walking? » What about pulling your hand away from fire? » What about watching TV? » What about day dreaming? 10 How to achieve AI? 11  How to achieve AI? » How is AI research done? » AI research has both theoretical and experimental sides. » The experimental side has both basic and applied aspects. » There are two main lines of research: One is biological, based on the idea that since humans are intelligent, AI should study humans and imitate their psychology or physiology. The other is phenomenal, based on studying and formalizing common sense facts about the world and the problems that the world presents to the achievement of goals. » The two approaches interact to some extent, and both should eventually succeed. It is a race, but both racers seem to be walking. [John McCarthy] 12 Branches of AI 13  Branches of AI » Logical AI » Search » Natural language processing » Pattern recognition » Knowledge representation » Inference From some facts, others can be inferred. » Automated reasoning 14  Branches of AI » Learning from experience » Planning To generate a strategy for achieving some goal » Ontology The study of the kinds of things that exist. In AI, the programs and sentences deal with various kinds of objects, and we study what these kinds are and what their basic properties are. » Genetic programming » Emotions! »… 15 AI foundations 16  The foundations of artificial intelligence – Part I » Philosophy Can formal rules be used to draw valid conclusions? How does the mind arise from a physical brain? Where does knowledge come from? How does knowledge lead to action? » Mathematics What are the formal rules to draw valid conclusions? What can be computed? How do we reason with uncertain information? 17  The foundations of artificial intelligence – Part II » Economics How should we make decisions to maximize the payoff? How should we do this when others may not go along? How should we do this when the payoff may be far in the future? » Neuroscience How do brains process information? » Psychology How do humans and animals think and act? 18  The foundations of artificial intelligence – Part III » Computer engineering How can we build an efficient computer? » Control theory and cybernetics How can artifacts operate under their own control? » Linguistics How does language relate to thought? 19 AI History 20  The history of artificial intelligence » The history of AI has had cycles of success, misplaced optimism, and resulting cutbacks in enthusiasm and funding. There have also been cycles of introducing new creative approaches and systematically refining the best ones. » AI has advanced more rapidly in the past decade because of greater use of the scientific method in experimenting with and comparing approaches. » Recent progress in understanding the theoretical basis for intelligence has gone hand in hand with improvements in the capabilities of real systems. The subfields of AI have become more integrated, and AI has found common ground with other disciplines. 21 Potted history of AI – Part I 1943 1950 1952—69 1950s 1956 McCulloch & Turing’s Look, Ma, no Early AI Dartmouth Pitts: Boolean “Computing hands! programs, meeting: circuit model Machinery including “Artificial of brain and Samuel's Intelligence” Intelligence” checkers adopted Neural program network 22 Potted history of AI – Part II 1965 1966— 1969— 1980— 1988— Robinson' 74 79 88 93 s AI Knowledg Expert Expert complete discovers e-based systems systems algorithm computatio systems industry industry for logical nal complexity booms busts: reasoning Neural ``AI network Winter'' research almost disappears 23 Potted history of AI – Part III 1985— 1988 1995 2003 2001- 2011- 95 Probabilit Agents, Human- Big data Deep Neural y agents, level AI Learning ALife, everywhe back on networks re … GAs, soft the return to computin agenda popularit g y Machine learning 24  Conclusion » Different people approach AI with different goals in mind. Two important questions to ask are: Are you concerned with thinking or behaviour? Do you want to model humans or work from an ideal standard? » In this course, we adopt the view that intelligence is concerned mainly with rational action. Ideally, an intelligent agent takes the best possible action in a situation. We study the problem of building agents that are intelligent in this sense. 25 Questions & Comments Abdel-Rahman Hedar [email protected] https://shorturl.at/ntI2x