Introduction to Artificial Intelligence (AI) PDF - CCAI 221: Fundamentals

Introduction CCAI 221: AI fundaments Assembled from: Artificial intelligence: a modern approach, Russel and Norving (pearson.com) http://aima.cs.berkeley.edu/ Inst. Ebtehal Alsaggaf Co...

Introduction CCAI 221: AI fundaments Assembled from: Artificial intelligence: a modern approach, Russel and Norving (pearson.com) http://aima.cs.berkeley.edu/ Inst. Ebtehal Alsaggaf Composed and edited by Shahd Alahdal 1 Outline:  What is AI?  Definitions  Approaches  The foundation of Artificial intelligence  The history of Artificial intelligence  The state of the art  Examples of AI Applications 2 What is AI ? definitions and approaches 3  What isIntelligence? The computational part of the (human) ability to achieve goals in the world Intelligent behavior involves: ability to act in complex environments ability to learn from experience ability to think and reason ability to perceive relations (in the world) ability to use tools (…) Varying kinds and degrees of intelligence occur in people, many animals , and even some machines 4 4  What is Artificial Intelligence (AI)? Definitions The science and engineering of making intelligent machines. (John McCarthy) The study of ideas that make people intelligent and incorporate those ideas into computers. (Patrick Henry) The study of making computers do things which, at the moment, people are better (Elaine Rich) Getting computers to do tasks that require human intelligence (Anonymous) 5 5  What is AI? Measure success compared to hu Measure of success against an man performance ideal measure – rationality processes and reasoning Thoughts Behavio rs 6 6  AIApproaches Four main approaches have been pursued The Turing Test approach (act like human ) The cognitive modelling approach (think like human ) The Laws of thought approach (think rationally ) The rational agent approach (act rationally ) The ultimate objective of these approaches is to build autonomous intelligent machines 7 7  Intelligence Test(Motivation) Computers can solve some difficult problems much more quickly than human Computing the GCD (Greatest Common Denominator) of two numbers Solving complex integration problems Computing product of, say, four numbers Humans can solve some simple problems much more elegantly than computers Navigating in a busy street Recognizing the voice and the image of a person The first law of AI Easy problems are hard and hard problems are easy 8 8  1. Acting humanly: The Turing Test approach Turing Test An interrogator communicates with a person and a computer The interrogator can’t see the person or computer The computer tries to fool the interrogator into believing that it is a human. The person also tries to convince the interrogator that it is human If the computer succeeds in fooling the interrogator, then it passes the intelligence test – intelligent computer 9 9  What would a computer need to pass the Turing test? 1. Natural language processing: to communicate with the interrogator. 2. Knowledge representation: to store and retrieve information provided before or during interrogation. 3. Automated reasoning: to use the stored information to answer questions and to draw new conclusions. 4. Machine learning: to adapt to new circumstances and to detect and extrapolate patterns. 5. Computer Vision (for total Turing test): to recognize the interrogator’s actions and various presented objects. 6. Robotics (for total Turing test): motor control and other senses to manipulate objects and move about. 10 10  2. Thinking Humanly: Cognitive science-based approach Simulate human-like thinking in machines by: Introspection: trying to catch our thoughts as they go Psychological experiments: Observing a Person in action Brain imaging: Observing the brain in action Develop theories and practice to build machines with human-like mind Emphasis is on the human reasoning process Cognitive science: combines computer models from AI and experimental techniques from psychology to construct testable theories of the human mind. 11 11  3. Thinking Rationally: The “Laws of thought" approach Develop systems that think rationally The focus is on logical rules and inference mechanisms that are provably correct and guarantee an optimal solution Example: Socrates is a man; all men are mortal; therefore, Socrates is mortal. 12 12  4. Acting Rationally: “The rational agent" approach Rational behavior: doing the right thing An agent is just something that acts. They are expected to operate autonomously, perceive their environment, persist over a prolonged period, and adapt to change. A rational agent acts to achieve the best outcome or when there is uncertainty, the best-expected outcome. The focus is on systems that act sufficiently, if not optimally, in all situations. 13 13  4. Acting Rationally: “The rational agent” approach The rational-agent approach has two advantages over the other approaches: 1. It is more general than the “low of thoughts” approach since correct inferences are just one of several possible mechanisms for achieving rationality. 2. It is more suitable for scientific development than approaches based on human behavior/thought. 14 The foundation of Artificial Intelligence 15  The Foundations of AI Philosophy: Given a mind that operates as a physical system, at least in part, according to logical rules Establish the source of knowledge (ex. Rationalism: the power of reasoning to understand the world). The mind is the connection between knowledge and action (thoughts). Mathematics: Theories of logic. Computation, algorithms, (un)decidability, (in)tractability Formal representation and proof Probability 16 16  The Foundations of AI Economics: Utility theory (make choices that leads to preferred outcomes) Decision theory (utility + probability) Neuroscience : Neuroscience is the study of the nervous system Neurons are cells that lead to thought, action, and consciousness Brains and digital computers have different properties 17 17  The Foundations of AI Psychology: Cognitive psychology: views the brain as an information-processing device Application of knowledge-based agent Computer engineering : Building powerful computers that make AI possible Linguistic: The meaning and structure of language (knowledge representation, grammar) Computational linguistic and NLP )Natural Language Processing) 18 The history of Artificial Intelligence 19  History of AI The beginning of artificial intelligence (1943–1955) 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" The birth of artificial intelligence (1956) 1956 Dartmouth meeting: "Artificial Intelligence" adopted, Early enthusiasm, great expectations (1952–1969) 1950s Early AI programs, including Samuel's Checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965 Robinson's complete algorithm for logical reasoning A dose of reality (1966–1973) 1966—73 AI discovers computational complexity Neural network research almost disappears Knowledge-based systems: The key to power? (1969–1979) 1969—79 Early development of knowledge-based systems.  History of AI AI becomes an industry (1980–present) 1980 AI becomes an industry 1980-88 Expert systems industry booms The Return of Neural Networks (1985–present) 1985 Neural networks return to popularity AI adopts the scientific method (1987–present) 1987-- AI becomes a science 1988-- Resurgence of probability; general increase in technical depth: speech technology, handwritten character recognition The emergence of intelligent agents (1995-present): 1995-- Researchers started to look “whole agent” problem again. Big data(2001–present) 2003-- Human-level AI back on the agenda. Deep Learning (20011–present) The state of the art Development of AI 22  State of the art Robotic vehicle: In 2005, A robotic car named STANLEY completed autonomously a 132-mile desert track at 22 mph in the DARPA challenge. In 2007, on streets with traffic on the Urban challenge. In 2018, Waymo test vehicles passed the landmark of 10 million miles driven on a public road without a serious accident, with the human driver taking over control only every 6000 miles. Soon after, the company began offering commercial robotic taxi services. In the air, autonomous fixed-wing drones have been providing cross- country blood delivery in Rwanda since 2016 Quadcopter, explore buildings while constructing 3D maps. 23 23  State of the art Legged locomotion BigDog, closely resembling an animal can move in irregular terrain and recover when slipping on an icy puddle. (2008) Atlas, a humanoid robot, not only walks on uneven terrain but jumps and does backflips. (2016) Autonomous planning and scheduling: During the Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people at a time. (1991) NASA's onboard autonomous planning program controlled the scheduling of operations for a spacecraft. (2000) SEXTANT system allows autonomous navigation in deep space beyond the global GPS. (2017) Every day, ride-hailing companies such as Uber and mapping services such as Google provide directions taking into account current and predicted future traffic conditions. 24 24  State of the art Machine translation: Online machine translation systems now enable the reading of documents in over 100 languages. Speech recognition: Alexa, Siri, Cortana, and Google offer assistants that can answer questions and carry out tasks for the users. (ex. Restaurant reservation). Recommendations: Companies such as Amazon, Facebook, Netflix, Spotify, YouTube, and Walmart use machine learning to recommend what you might like based on your experience and those of others like you. Spam filtering can be considered a form of recommendation. 25 25  State of the art Game playing: Deep Blue defeated the world chess champion Garry Kasparov (1997) Human champions have been beaten by AI in the Jeopardy game. (2010) Image understanding: Not content with exceeding human accuracy on the challenging ImageNet object recognition task. Current systems are far from perfect. (ex: “a refrigerator filled with lots of food and drinks” turned out to be “ no parking sign partially obscured with lots of small stickers “ 26  State of the art Medicine: AI algorithms now equal or exceed expert doctors at diagnosing many conditions, particularly when the diagnosis is based on images. (2016) (ex: Alzheimer's disease, metastatic cancer, skin diseases…) Climate science: Machine learning can be used to tackle climate change. (2018) 27 Risks and Benefits of AI 28  Benefits of AI Free humanity from menial repetitive work Dramatically increase the production of goods and services Help with finding cures for diseases Help with finding solutions for climate changes 29  Risks of AI Lethal autonomous weapons Surveillance and persuasion Biased decision making Safety-critical applications Cyber security 30  State of the art Which of the following can be done at present? Play a decent game of table tennis Play a decent game of Jeopardy Win against humans at Chess Drive safely along the highway Buy a week's worth of groceries on the web Discover and prove a new mathematical theorem Write an intentionally funny story Translate spoken Chinese into spoken English in real-time Converse successfully with another person for an hour Perform a complex surgical operation Unload any dishwasher and put everything away 31 31 Examples of AI applications 32 Examples of AI Application systems: Game Playing Deep Blue chess program beat world champion Gary Kasparov 33 33 Examples of AI Application systems: Self-driving car From: https://www.eescorporation.com/do-self-driving-cars-use-ai/ 34 Examples of AI Application systems: Natural Language Understanding AI Translators – spoken to and prints what one wants in foreign languages. Natural language understanding (spell checkers, grammar checkers) 35 35 Examples of AI Application systems: Diagnostic Systems WebMD Symptom Checker. A web medical diagnostic system at https://symptoms.webmd. com 36 36 Examples of AI Application Systems: Robotics (SOFIA): Robotics becoming increasingly important in various areas like games, to do tedious jobs among other things. From: https://www.vapulus.com/en/15-main-types-of-robotics/ 37 37 Summary 38  Summary AI is the science of building intelligent machines. Main AI approaches can be classified as Turing test-based approach (acting humanly), Cognitive science-based approach (thinking humanly), Laws of thought-based approach (thinking rationally), and Rational agent-based approach (acting rationally). Some disciplines that contributed ideas, viewpoints, and techniques to AI include psychology, mathematics, linguistics… The history of AI has cycles of introducing new creative approaches and systematically refining the new ones. Some main application areas of AI include game playing, natural language processing, speech recognition, machine vision, robotics, and expert Systems. 39 39  Reference Book: Artificial intelligence: a modern approach by Stuart Russel and Peter Norving (Chapter 1) 40