LM#1_lntro to AI.pdf

Artificial Intelligence: Principles & Techniques ARTI 401 Chapter (1) Intro to Artificial Intelligence Dr.Dina Alabbad Artificial Intelligence: A...

Artificial Intelligence: Principles & Techniques ARTI 401 Chapter (1) Intro to Artificial Intelligence Dr.Dina Alabbad Artificial Intelligence: A Modern Approach- Peter Norvig and Stuart J. Russell AI: Principles & Techniques Objectives At the end of the class, you should be able to: ❑ Explain why we consider Artificial intelligence (AI) to be a subject most worthy of study, ❑ Identify the goals of Artificial Intelligence ❑ Decide what exactly AI. ❑ Describe what an intelligent agent is AI: Principles & Techniques 2 Outline 1.1 What Is AI? 1.2 The Foundations of Artificial Intelligence 1.3 The History of Artificial Intelligence 1.4 The State of the Art 1.5 Summary AI: Principles & Techniques 3 Chapter 1: Intro to Artificial Intelligence What Is AI? The Foundations of Artificial Intelligence The History of Artificial Intelligence The State of the Art AI: Principles & Techniques 4 Basic Questions What is Intelligence? Can a machine be “intelligent”? What’s involved in Intelligence? What can AI do today? Why is AI research important? Current Challenges - what makes AI problems hard? How can we make computer-based systems more intelligent? AI: Principles & Techniques 5 Intelligence As humans, we try to understand (how we think), our intelligence. In the field of AI, it attempts not just to understand but also to build intelligent entities. Is it something which characterize humans? Or is there any absolute standard of judgment? AI: Principles & Techniques 6  What is Intelligence ? Intelligence is the ability to learn about, to learn from, to understand about, and interact with one’s environment. Intelligence is the ability of understanding Intelligence is not to make no mistakes but quickly to understand how to make them good (German Poet) Characteristics of Intelligence (1) Ability to Communicate (2) Creativity (3) Internal Knowledge (4) Ability to Learn (5) Perceive World Knowledge (6) Goal-Directed Behavior (7) Self Awareness AI: Principles & Techniques 7 Intelligence Someone’s intelligence is their ability to understand and learn things. Intelligence is the ability to think and understand instead of doing things by instinct or automatically. Thinking is the activity of using your brain to consider a problem or to create an idea. AI: Principles & Techniques 8 A Hierarchical Model of Intelligence Wisdom + Vision Knowledge Information + Experience Data + Context 9 Intelligent System Should do: ▪ How can we make computer-based systems more intelligent? ▪ In practical terms, intelligent systems: ▪ Should have the ability to automatically perform tasks that normally require a human expert. ▪ Should have more autonomy; less requirement for human intervention or monitoring. ▪ Should have flexibility in dealing with variability in the environment in an appropriate manner. ▪ Are easier to use able to understand what the user wants from limited instructions. ▪ Can improve their performance by learning from experience. Intelligent Systems in Your Everyday Life AI is used in day-to-day activities such as: Post Office ▪ Automatic address recognition and sorting of mail ▪ Banks ▪ Automatic check readers, signature verification systems ▪ Automated loan application classification ▪ Telephone Companies ▪ Automatic voice recognition for directory inquiries ▪ Automatic fraud detection ▪ Credit Card Companies ▪ Automatic fraud detection ▪ Computer Companies ▪ Automatic diagnosis for help-desk applications 11  Intelligent Agent INTERNAL INPUTS PROCESSES Senses environment Has Knowledge Has understanding/ intentionality See Hear Touch Can Reason Taste Smell Exhibits behavior OUTPUTS Goals of AI Why is AI research important? Scientific goal: to understand the principles that make intelligent behavior possible in natural or artificial systems. analyze natural and artificial agents formulate and test hypotheses about what it takes to construct intelligent agents. design, build, and experiment with computational systems that perform tasks that require intelligence. Engineering goal: (Cognitive aspect) design useful, intelligent artifacts. To understand what kind of computational mechanisms are needed for modeling intelligent behavior. AI: Principles & Techniques 13 So, what general principles should we use to achieve these goals? Perceiving, recognizing, understanding the real world Reasoning and planning about the external world Learning and adaptation Four schools of thoughts (Russel & Norvig) Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally Figure 1.1 some definitions of AI, organized into four categories. AI: Principles & Techniques 14  What Is Artificial Intelligence? These definitions provide 4 different overviews, or approaches, to understand AI. Thinking Humanly Thinking Rationally ▪ "The exciting new effort to make computers ▪ "The study of mental faculties through the use think...machine with minds, in the full and literal of computational models"(Charnaik and Mc sense."(Haugeland,1985) Dermott, 1985). ▪ "[The automation of] activities that we associate ▪ "The study of the computations that make it with human thinking, activities such as decision- possible to perceive, reason, and act." (Winston, making, problem solving, learning...." 1992) (Hellmman,1978) Acting Humanly Acting Rationally ▪ "The art of creating machines that perform ▪ "Computational Intelligence is the study of functions that require intelligence when design of intelligent agents." (Poole et at, 1998) performed by people." (Kurzweil, 1990) ▪ "AI... is concerned with intelligent behavior in ▪ "The study of how to make computers do things artifects." (Nulsoon, 1998) at which, at the moment, people are better." (Rich and Knight,1991) What Is Artificial Intelligence? Human-Based Ideal Rationality Systems that think like Systems that think Reasoning-Based: humans. rationally. Systems that act like Systems that act Behavior-Based: humans. rationally. Four Possible Goals for AI According to AIMA 16  Acting Humanly (Turing Test) Can a machine be truly “intelligent”? : Turing’s Test Test composed of : ▪ An interrogator (a person who will ask questions) ▪ a computer (intelligent machine !!) ▪ A person who will answer to questions B ▪ A curtain (separator) A ▪ Alan Turing's 1950 article in Computing Machinery and Which one’s the Intelligence discussed conditions for considering a machine to be computer? intelligent ▪ Can someone tell which is the machine, when communicating to human and to a machine in another room? If not, can we call the machine intelligent? ▪ The Turing test is a test of a machine's ability to demonstrate intelligence. ▪ The computer passes the “test of intelligence” if a human, after posing some written questions, cannot tell whether the responses were from a person or not. Acting Humanly: The Turing Test approach Turing (1950) "Computing machinery and intelligence": "Can machines think?" → "Can machines behave intelligently?" Operational test for intelligent behavior: the Imitation Game Suggests major components required for AI: - knowledge representation - reasoning, - language/image understanding, - learning * Question: is it important that an intelligent system act like a human? What would a computer need to pass the Turing test? Passing Turing test requires the computer to have the following capabilities: 1. NLP – it can communicate in English with the examiner 2. Knowledge Representation - to store information provided during the test 3. Automated reasoning - to use stored information to answer questions and draw conclusions. 4. Machine learning - to adapt to changes and extrapolate (reason) patterns. However, the Turing test excludes direct physical contact between the machine and the tester. The so called the Total Turing test brings forward two more requirements: 5. Computer vision - to recognize the examiner’s actions and various objects presented by the examiner. 6. Robotics - to move and act upon objects as requested.  Exercise : Captcha Completely Automated Public Turing test to tell Computers and Humans Apart https://cupdf.com/document/captcha- completely-automated-public-turing-test-to- tell-computers-and-humans.html Exercise: give me examples of capcha? AI: Principles & Techniques 20 Thinking Humanly: The Cognitive Modeling Approach Cognitive Science approach – Try to get “inside” minds This involves trying to understand human thought and an effort to build machines that emulate human thought process. Requires to know how humans think? This view is the cognitive science approach to AI. ▪ Cognitive Science: Combination of computer models from AI and experimental techniques from psychology to construct precise and testable theories of human mind. Hence, all three fields share one principal direction! Problems – Humans don’t behave rationally – The reverse engineering is very hard to do – The brain’s hardware is very different to a computer program  The “Law of thought” approach Think Rationally: The Law of thought approach Aristotle ( right thinking) : always gave correct conclusions given correct premises This approach is related to LOGIC, that is ,logical rules make the mental mind of humans. Represent facts about the world via logic ▪ Syllogism: Example: Socrates is a man %Fact All men are mortal % Rule if X is a Man, then X is Mortal Therefore Socrates is mortal % Inference ▪ Logic: ▪ Precise notation for statements about all kinds of objects in the world and the relation among them. ▪ Drawbacks ▪ Not easy to take informal knowledge and state it in formal terms required by logical notation. When problem is less than 100% certain. ▪ Difference between solving problem in principal and solving it in practice. AI: Principles & Techniques 22 Acting Rationally: The rational Agent approach ▪ An agent : Operate autonomously Perceive their environment Persists over prolonged time period Adapt to change, create and pursue goals ▪ The Rational Agent: is one that acts to achieve the best outcome or best expected outcome if there is uncertainty. ▪ Thinking Rationally (Laws of Thought is a part of acting rationally) ▪ Correct inference is not all of rationality. ▪ Advantages: ▪ More general than the laws of thought ▪ Because correct inference is just one of several possible mechanisms for achieving rationality. ▪ More amenable to scientific development than human thought and behavior. Rational Agents Rational behavior: Doing that was is expected to maximize one’s “utility function” in this world. A rational agent acts rationally. This course is about designing rational agents Abstractly, an agent is a function from percept histories to actions: [f: P* → A] For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance Caveat: computational limitations make perfect rationality unachievable → design best program for given machine resources Commonly Accepted Definitions of Artificial Intelligence ▪ Winston: “AI is the study of ideas which enable computers to do things which make people seem intelligent.” ▪ Steven Tanimoto, “Computational techniques for performing tasks that apparently require intelligence when performed by humans.” ▪ David Parnas, “Artificial intelligence is to artificial flowers as natural intelligence is to natural flowers.” ▪ Rich: “AI is the study of how to make computers do things which, at the moment, people do better.” ▪ Fahlman: “AI is the study of intelligence using the ideas and methods of computation.” AI: Principles & Techniques 25 Artificial Intelligence ▪ AI is the reproduction of the methods or results of human reasoning or intuition. ▪ Artificial Intelligence is a branch of Computer Science concerned with the automation of intelligent behaviour. ▪ Artificial Intelligence is concerned with the design of intelligence in an artificial device. ▪ The art of creating machines that perform when functions that require intelligence performed by people. ▪ AI is the study of systems that act in a way that to any observer would appear to be intelligent. ▪ AI is a field of computer science that simulates human performance to make a computer reasons in a manner similar to humans. AI: Principles & Techniques 26 Applied Areas of AI  Game playing  Speech and language processing  Expert reasoning  Planning and scheduling  Vision  Robotics AI: Principles & Techniques 27 AI: Principles & Techniques 28 Human Intelligence VS Artificial Intelligence Human Intelligence VS Artificial Intelligence (PROS) Human Intelligence VS Artificial Intelligence (PROS) Human Intelligence Artificial Intelligence ▪ Intuition, Common sense, ▪ Ability to simulate human Judgment, Creativity, behavior and cognitive Beliefs etc. processes ▪ The ability to demonstrate ▪ Capture and preserve their intelligence by human expertise communicating effectively ▪ Possible Reasoning and ▪ Fast Response. The ability Critical thinking to comprehend large amounts of data quickly. Major question: How are we going to get a machine to act intelligently to perform complex tasks? AI: Principles & Techniques 31 AI is a Multi-Disciplinary Field The Foundations of Artificial Intelligence Philosophy Mathematics Economics Neuroscience Psychology Computer engineering Control theory and cybernetics Linguistics Foundations of Artificial Intelligence Philosophy e.g., foundational issues (can a machine think?), issues of knowledge and believe, mutual knowledge Psychology and Cognitive Science e.g., problem solving skills Neuro-Science e.g., brain architecture Computer Science And Engineering e.g., complexity theory, algorithms, logic and inference, programming languages, and system building. Mathematics and Physics e.g., statistical modeling, continuous mathematics, Statistical Physics, and Complex Systems. AI: Principles & Techniques 33 Disciplines relevant to AI Philosophy Can formal rules be used to draw valid conclusions? Where does knowledge come from? How does knowledge lead into action? Mathematics/Statistics What are the formal rules to draw valid conclusion? How do we reason with uncertain information? How do intelligent agents learn? Economics How should we make decisions to maximize payoff? How should we do this when others are making decisions too? AI: Principles & Techniques 34 Disciplines relevant to AI Psychology How do humans and animals think? Computer How can we build efficient computers? Linguistics How does language relate to thoughts? knowledge representation, grammar AI: Principles & Techniques 35 History of AI AI: Principles & Techniques 36 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  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 Success Stories Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 AI program proved a mathematical conjecture (Robbins's conjecture) unsolved for decades During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft Proverbsolves crossword puzzles better than most humans Robot driving: DARPA grand challenge 2003-2007 2006: face recognition software available in consumer cameras 2013: Social network behavior Example: DARPA Grand Challenge Grand Challenge – Cash prizes ($1 to $2 million) offered to first robots to complete a long course completely unassisted – Stimulates research in vision, robotics, planning, machine learning, reasoning, etc 2004 Grand Challenge: – 150 mile route in Nevada desert – Furthest any robot went was about 7 miles – … but hardest terrain was at the beginning of the course 2005 Grand Challenge: – 132 mile race – Narrow tunnels, winding mountain passes, etc – Stanford 1st, CMU 2nd, both finished in about 6 hours 2007 Urban Grand Challenge – This November in Victorville, California What’s involved in Intelligence? Speech synthesis, recognition and understanding – very useful for limited vocabulary applications – unconstrained speech understanding is still too hard Computer vision – works for constrained problems (hand-written zip-codes) – understanding real-world, natural scenes is still too hard Learning – adaptive systems are used in many applications: have their limits Planning and Reasoning – only works for constrained problems: e.g., chess – real-world is too complex for general systems Overall: – many components of intelligent systems are “doable” – there are many interesting research problems remaining AI Applications ▪ Language translation services (Google) ▪ News aggregation and summarization (Google) ▪ Speech recognition (Nuance) ▪ Song recognition (Shazam) ▪ Face recognition (Recognizr) ▪ Image recognition (Google Goggles) ▪ Question answering (Apple Siri, IBM Watson) ▪ Chess playing (IBM Deep Blue) ▪ 3D scene modeling from images (Microsoft Photosynth) ▪ Driverless cars (Google, Tesla, etc.) ▪ Chatbot (Amy A.I.) ▪ Augmented reality travel guide (mTrip) State of AI Systems in Practice Email communications Email Filters Smart Replies Social media Chatbots Facebook Proactive Detection Web searching Google Predictive Searches Youtub's Algorithm Stores and services Maps and Directions Product Recommendations - Amazon , Netflix Commercial Airline Flights Banking Digital voice assistants AI: Principles & Techniques 44  State of th e a r t Which of the following can be done at present?​ Play a decent game of table tennis​ Drive safely along a curving mountain road​ Drive safely along Telegraph Avenue​ Buy a week’s worth of groceries on the web​ Buy a week’s worth of groceries at Berkeley Bowl​ Play a decent game of bridge​ Discover and prove a new mathematical theorem​ Design and execute a research program in molecular biology​ Write an intentionally funny story​ Give competent legal advice in a specialized area of law​ Translate spoken English into spoken Swedish in real time​ Converse successfully with another person for an hour​ Perform a complex surgical operation​ Unload any dishwasher and put everything away​  State of th e a r t Which of the following can be done at present?​ Play a decent game of table tennis Drive safely along a curving mountain road Drive safely along Telegraph Avenue Buy a week’s worth of groceries on the web Buy a week’s worth of groceries at Berkeley Bowl Play a decent game of bridge Discover and prove a new mathematical theorem Design and execute a research program in molecular biology Write an intentionally funny story Give competent legal advice in a specialized area of law Translate spoken English into spoken Swedish in real time Converse successfully with another person for an hour Perform a complex surgical operation Unload any dishwasher and put everything away Research directions of AI Today there are 2 main research directions in artificial intelligence: (1) Bionics: approaches that have focus on humans and based on empirical knowledge acquired during different experiments. (2) Pragmatic Development Of Computer Programs: approaches based on rationality and combining mathematics and computer engineering. AI: Principles & Techniques 47 Related research fields ▪ Knowledge representation ▪ Reasoning and automatic proving ▪ Search and optimization ▪ Problem solving ▪ Learning and understanding ▪ Pattern classification / recognition ▪ Planning AI: Principles & Techniques 48 Further Issues on Related to AI and its effects on Societies ❖ The future of AI ❖ The social aspect of overdependent on AI (e.g., unemployment) ❖ What if AI finally gets deployed into war equipment? The consequences? -imagine a self evolving weapon that defy human control? Many questions: Can AI save us from the unemployment crisis and growing poverty? Whether ethical AI can be used as a tool to augment human intelligence rather than to replace it. AI: Principles & Techniques 50 AI and the future of work Source: Maestro Strategies 51 AI Questions Can we make something that is as intelligent as a human? Can we make something that is as intelligent as a bee? Can we make something that is evolutionary, self improving, autonomous, and flexible? Can we start a new industry of handwriting recognition agents? what makes AI problems hard? Computation (time/memory) Information (data) How do we solve tackle these challenging problems? 52  Some relevant people in AI Asimov Clark McCarthy Some relevant people in AI Minsky Michie Newell Simon Turing AI: Principles & Techniques 54 Summary What AI systems? Turing test Act Rationally →expects to maximize goal achievement Popular AI systems Birth of AI in the 1950s Broad field of subdomains and combination of disciplines Central role: symbols and knowledge representation Knowledge-based systems and intelligent agents are core concepts in AI AI: Principles & Techniques 55 Summary Artificial Intelligence involves the study of: automated recognition and understanding of speech, images, etc learning and adaptation planning, reasoning, and decision-making AI has made substantial progress in recognition and learning some planning and reasoning problems AI Applications improvements in hardware and algorithms => AI applications in industry, finance, medicine, and science. AI Research many problems still unsolved: AI is a fun research area! AI: Principles & Techniques 56 Questions 1) Define intelligence. 2) Why Would You Study Artificial Intelligence? 3) What are the different approaches in defining artificial intelligence? 4) Suppose you design a machine to pass the Turing test. What are the capabilities such a machine must have? 5) Design ten questions to pose to a man/machine that is taking the Turing test. 6) Do you think that building an artificially intelligent computer automatically shed light on the nature of natural intelligence? 7) List 5 tasks that you will like a computer to be able to do within the next 5 years. 8) List 5 tasks that computers are unlikely to be able to do in the next 10 years. AI: Principles & Techniques 57 Recap What have we learned in week 1? Next lecture Four schools of thoughts (Russel & Norvig) Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally 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 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. AI: Principles & Techniques 58  What is AI? Modeling exactly how humans actually think cognitive models of human reasoning Modeling exactly how humans actually act models of human behavior (what they do, not how they think) Modeling how ideal agents “should think” models of “rational” thought (formal logic) note: humans are often not rational! Modeling how ideal agents “should act” rational actions but not necessarily formal rational reasoning i.e., more of a black-box/engineering approach Modern AI focuses on the last definition we will also focus on this “engineering” approach success is judged by how well the agent perform -- modern methods are inspired by cognitive & neuroscience (how people think). 59 Acting Humanly Test composed of : ▪ An interrogator (a person who will ask questions) ▪ a computer (intelligent machine !!) ▪ A person who will answer to questions ▪ A curtain (separator) Alan Turing's 1950 article in Computing Machinery and Intelligence discussed conditions for considering a machine to be intelligent The Turing Test Can Machine think? A. M. Turing, 1950) Requires :(To act humanly? ) Natural language Knowledge representation Automated reasoning Machine learning Computer Vision Robotics for full test Turing test: ultimate test for acting humanly Computer and human both interrogated by judge Computer passes test if judge can’t tell the difference AI: Principles & Techniques 61 Exercise How Alan Turing laid the foundations for AI: The Turing test explained Turing, Alan M. “Computing machinery and intelligence.” Parsing the turing test. Springer, Dordrecht, 2009. 23–65. 62 Inspirations for AI 1. Logic Studied intensively within mathematics Gives a handle on how to reason intelligently Example: automated reasoning Proving theorems using deduction Advantage of logic: We can be very precise (formal) about our programs Disadvantage of logic: Not designed for uncertainty. AI: Principles & Techniques 63 Inspirations for AI 2. Introspection Humans are intelligent, aren’t they? Expert systems Implement the ways (rules) of the experts Example: MYCIN (blood disease diagnosis) Performed better than junior doctors AI: Principles & Techniques 64 Inspirations for AI 3. Brains Our brains and senses are what give us intelligence Neurologist tell us about: Networks of billions of neurons Build artificial neural networks In hardware and software (mostly software now) Build neural structures Interactions of layers of neural networks http://www.youtube.com/watch?v=r7180npAU9Y&NR=1 AI: Principles & Techniques 65 AI: Principles & Techniques 66 Exercise : Intelligent Agents 68  Intelligence/Rationality Russell sees AI as the field devoted to building intelligent agents, which are functions taking as input tuples of percepts from the external environment and producing behavior (actions) on the basis of these percepts. Russell’s overall picture is this one: The Basic Picture Underlying Russell’s Account of Intelligence/Rationality 69 Intelligent Behavior: Examples Learn to flip pancakes Object Tracking roboclean talk roboclean action Watson Game Show Watson U.S. cities AI: Principles & Techniques 70 Addental Resources Artificial Intelligence, the History and Future - with Chris Bishop https://www.youtube.com/c/ahmedyousry609/playlists AI: Principles & Techniques 71