Class Notes CIS 675 Artificial Intelligence: Overview CIS 675 Péter Molnár, 2003 (all rights reserved) Slide 1 AI: Overview An Attempt to classify Foundation Modern topics CIS 675 Péter Molnár, 2003 (all rights reserved) Slide 2 AI Overview: An Attempt to Classify An Attempt to Classify Two approaches: human-centered vs. rationality. Both directions have yielded some valuable insights. A human-centered approach is empirical science, involving hypothesis and experimental confirmation. A rationalist approach involves a combination of mathematics and engineering. Both approaches can be broken up into fields that are concerned with – the thought process and reasoning, or – the behavior. CIS 675 Péter Molnár, 2003 (all rights reserved) Slide 3 AI Overview: An Attempt to Classify Four Categories of AI Systems that think like humans. Systems that think rationally. Systems that act like humans. Systems that act rationally. CIS 675 Péter Molnár, 2003 (all rights reserved) Slide 4 AI Overview: An Attempt to Classify Acting humanly Turing Test, proposed by Alan Turing (1950). Turing’s definition of intelligent behavior as the ability to achieve human-level performance in all cognitive tasks. The test involves an interrogator who interacts with one human and one machine. Within a given time the interrogator has to find out which of the two is the human, and which one the machine. Issue to solve in order to pass the test using a terminal: natural language processing, knowledge representation automated reasoning, machine learning. Additional requirements for the “total Turing test”: computer vision, speech recognition, speech synthesis, robotics. CIS 675 Péter Molnár, 2003 (all rights reserved) Slide 5 AI Overview: An Attempt to Classify Thinking humanly Need to understand how humans think. Methods: catch our thoughts while they go by – psychological experiments Example: GPS, “General Problem Solver” (Newell and Simon, 1961). Objective to compare the

Lire le document entier