Artificial Intelligence (AI) Lecture 2 - Introduction PDF

ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL ARTIFICIAL INTELLIGENCE (AI) INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) Lecture 2 - Introduction Dr. Sarah M. Ayyad ARTIFICIAL INTELLIGENCE (AI) October 2024  /(AI) 02. What is inte...

ARTIFICIAL INTELLIGENCE (AI) ARTIFICIAL ARTIFICIAL INTELLIGENCE (AI) INTELLIGENCE (AI) ARTIFICIAL INTELLIGENCE (AI) Lecture 2 - Introduction Dr. Sarah M. Ayyad ARTIFICIAL INTELLIGENCE (AI) October 2024  /(AI) 02. What is intelligence?  Intelligence ▪ The faculty of adapting one's self to circumstances. ~ Alfred Binet (a French psychologist who invented the first practical test (IQ)) ▪ The resultant of the process of acquiring, storing in memory, retrieving, combining, comparing, and using in new contexts information and conceptual skills. ~ Lloyd Humphreys (an American psychologist)  /(AI) 03. What is Artificial Intelligence?  It is the science and engineering of making intelligent machines, especially intelligent ARTIFICIAL computer programs. The goal of AI is to develop machines that behave as though they were intelligent. INTELLIGENCEJohn McCarthy, Stanford University (AI)  Four possible definitions Four main approaches that have been followed. Think like Think people Rationally (Think humanly) Act like Act people Rationally (Acting ARTIFICIAL INTELLIGENCE (AI) humanly)  1. Think Humanly Thinking humanly (Cognitive modeling) ▪ ARTIFICIAL Thinking humanly means trying to understand and model how the human mind works. ▪ ▪ Example: Neural Networks. INTELLIGEN An interdisciplinary field of cognitive science. CE (AI) 1. Think Humanly ARTIFICIAL INTELLIGEN CE (AI)  2. Acting Humanly ▪ The study of how to make computers do things ▪ at which, people are better. ARTIFICIAL Example: Natural Language Processing to enable It to communicate successfully in English (or INTELLIGEN some other human language), Robotics to manipulate objects and move about CE (AI)  2. Acting Humanly The Turing Test approach This is a problem that has greatly troubled AI researchers for being intelligent?” ARTIFICIAL years. They ask the question “when can we count a machine as The most famous response is attributed to Alan Turing, a British INTELLIGEN mathematician. The famous “Turing Test” was named after him. To date, no program has yet passed the Turing Test! However, there is the annual Prize which awards scientists for getting close. CE (AI) In order to pass the Turing Test, a program that succeeded would need to be capable of: speech recognition, natural language understanding, knowledge representation; learning; and automated reasoning and decision making. 2. Acting Humanly ARTIFICIAL INTELLIGEN CE (AI)  3. Thinking Rationally Idealized or “right” way of thinking. The “thinking rationally” approach to AI uses ARTIFICIAL symbolic logic to capture the laws of rational thought as symbols that can be manipulated. INTELLIGEN Reasoning involves manipulating the symbols according to well-defined rules, kind of like algebra. Problems with this approach. CE (AI) Computational complexity of finding the solution Describing real-world problems and knowledge in logical notation Dealing with uncertainty  4. Acting Rationally Acting Rationally (Rational Agents) ▪ Our focus here: rational agents systems which ARTIFICIAL make the best possible decisions given goals and constraints. INTELLIGEN ▪ Not necessary to do the best action; an action that is good enough is acceptable. ▪ Agent = architecture + software. ▪ Example: game playing CE (AI)  ARTI THANKS CIAL Do you have any questions? [email protected] INTE CREDITS: This presentation template was created by Slidesgo Flaticon Slidesgo, including icons by Flaticon and infographics & images by Freepik Freepik IGEN