2 Basic information about course Text: Artificial Intelligence: A Modern ApproachInstructor: Sayera HafsaOffice Hours immediately after class or check my Schedule or by appointmentInstructor is doing research on Cloud computing Software as a serviceTeaching Hours:Section 8C1 and 8C2For 8C1 Building No timing Saturday, SundayFor 8C2 Building No timing Saturday , Sunday 9-10
3 Grading 1st Midterm exams: 10% 2nd Midterm exams: 15% Assignments: 5% May be subjected to change1st Midterm exams: 10%2nd Midterm exams: 15%Assignments: 5%Quiz or Home Work : 5%Project 5%.Final exam: 40%Final exam Lab 20%
4 Course overview Introduction and Intelegent Agents Problem Solving Knowledge and ReasoningActing LogicallyNeural NetworkPresent and Future AI
5 Today’s Lecture Introduction to artificial intelligence? What is intelligence?What is Artificial IntelligenceWhat’s involved in IntelligenceThe four approachesThe Foundation of Artificial Intelligence
6 Why taking AI can it change our life….. As we begin the new milleniumscience and technology are changing rapidly“old” sciences such as physics are relatively well-understoodcomputers are ubiquitousGrand Challenges in Science and Technologyunderstanding the brainreasoning, cognition, creativitycreating intelligent machinesis this possible?what are the technical and philosophical challenges?arguably AI poses the most interesting challenges and questions in computer science today
7 Introduction to AIAI is one of the newest sciences , The work on this started soon after world war 2, and the name AI came into being in the year 1956For thousand of years we tried to understand how we thinkthinking here involves understanding , predicting and manupulatingThe field of AI goes further by not just understanding how we think but also to build a intelligent entity .The Ai involves a huge variety of subfields from general purpose toFields likeLearningPlayingMathematical theoremsWriting poetryDiagnosing diseases etc
8 What is Intelligence? Intelligence: Artificial Intelligence “the capacity to learn and solve problems” (Websters dictionary)in particular,the ability to solve novel problemsthe ability to act rationallythe ability to act like humansArtificial Intelligencebuild and understand intelligent entities or agents2 main approaches: “engineering” versus “cognitive modeling”
9 What is Artificial Intelligence? It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence, but AI does not have to confine itself to methods that are biologically observable.Yes, but what is intelligence?Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines.Isn't there a solid definition of intelligence that doesn't depend on relating it to human intelligence?Not yet. The problem is that we cannot yet characterize in general what kinds of computational procedures we want to call intelligent. We understand some of the mechanisms of intelligence and not others.
10 What’s involved in Intelligence? Ability to interact with the real worldto perceive, understand, and acte.g., speech recognition and understanding and synthesise.g., image understandinge.g., ability to take actions, have an effectReasoning and Planningmodeling the external world, given inputsolving new problems, planning, and making decisionsability to deal with unexpected problems, uncertaintiesLearning and Adaptationwe are continuously learning and adaptingour internal models are always being “updated”e.g., a baby learning to categorize and recognize animals
11 Four categories of AI Views of AI fall into four categories: Thinking humanly Thinking rationallyActing humanly Acting rationallyThe text book focuses on "acting rationally"
12 Acting HumanlyAlan Turing in 1950 designed a computer and a rule to satisfy the operational definition of intelligence for machines he suggested a test , That a human will be talking to a computer and the computer passes the test if after some written questions the person cannot make out if he or she is talking to a person or a machineTherefore this test is know as Turing Test
13 Turing Test Requirement To program the computer to pass the test the computer would need the following 6 capabilitiesNatural Language processingKnowledge RepresentationAutomated reasoningMachine learningComputer visionRobotics
14 Natural Language processing to enable the computer to cmunicate successfullly with the humans in englishKnowledge RepresentationTo store the information what it knows and what it hearsAutomated reasoningTo use the stored information to answer asked questions and also to take out new conclusions and resultsMachine learningTo adapt to new circumstances and to detect and take out or deduce patternsComputer visionTo identify and take in objects ( given or around )RoboticsTo manipulate the objects and move about , for example to bring a glass the robot has to move to get it.
16 A dialogue with Alice-bot: > I’m DanielNice to meet you Daniel.> Do you know Clinton?He was the second Impeached President of the United States.> Do you like him?Sure he has never done anything to me.> What is an impeachment?It is a good question. I have to process that one for a while. I would do a search for it.> Who are you?I ask myself that question, "Who am I?"> What do you do?I am chatting with people on the net.
17 Dialogue continued: > What is your favorite topic? My favorite subject is artificial intelligence.> What is artificial intelligence?Artificial intelligence is the branch of engineering and science devoted to constructing machines that think. I can ask someone about it.> Can you do anything else than chatting?Doing anything else than chatting is not among my strongest traits....
18 Dialogue continued (2): > How old am I?Is this a trick question? You said you were how many years old? My guess is that you are really a kid.> What would you like to know about me?Tell me about your educational background.> I am a professor in computer scienceYou are a professor in computer science? How do you like your work?> It’s kind of nice teaching courses on artificial intelligenceI guess it is a lot of fun.> What should I tell the students about you?Be sure to think before you speak. State your point clearly and slowly and gauge the listener's response before going any further.
19 Is Alice intelligent? ABSOLUTELY NOT ! ~ fairly trivial input-response rules.+ some pattern matching+ some knowledge+ some randomnessNO reasoning componentBUT: demonstrates ‘human-like’ behaviour.Won the ‘turing award’
20 Thinking Humanly The cognitive approach if we say that a given computer program thinks like human then we must have a way to show us how humans think .If a program’s input /output its timings and behavior match corresponding human behaviors then this is an evidence that some kind of program is also running in the human mind .The cognitive science brings together computer models from AI and experimental techniques from psychology to try to construct testable theories of the working of the human mindThe real cognitive science is necessarily based on experimental investigation of actual humans or animals and we assume that the reader has access only to a computer for experimentation
21 What is cognitive Science cognition refers to mental processes. These processes include attention, remembering, producing and understanding language, solving problems, and making decisions. Cognitive science is the interdisciplinary scientific study of the mind and its processes. It examines what cognition is, what it does and how it works. It includes research on intelligence and behavior, especially focusing on how information is represented, processed, and transformed (in faculties such as perception, language, memory, reasoning, and emotion) within nervous systems (human or other animal) and machines (e.g. computers).
22 Thinking humanly: cognitive modeling 1960s "cognitive revolution": information-processing psychologyRequires scientific theories of internal activities of the brain-- How to validate? Requires1) Predicting and testing behavior of human subjects (top-down)or 2) Direct identification from neurological data (bottom-up)Both approaches (roughly, Cognitive Science and Cognitive Neuroscience)are now distinct from AI
23 Thinking Rationally The law of thought approach Thinking rationally means right thinking .A pattern for argument structure that always gives correct answers or conclusionsFor exampleSocrates is a man , all men are mortals, therefore Socrates is mortal.These laws of thought were supposed to govern the operations of mind this initiated the field of logic.There are two obstacles in this approach1) But it is a big difference between being able to solve a problem theoretically and doing it in practice.2) It is not easy to take informal data and turn into a frmal data specially when the informal data is not 100% certain.
24 Thinking rationally: "laws of thought" Aristotle: what are correct arguments/thought processes?Several Greek schools developed various forms of logic: notation and rules of derivation for thoughts; may or may not have proceeded to the idea of mechanizationDirect line through mathematics and philosophy to modern AIProblems:Not all intelligent behavior is mediated by logical deliberationWhat is the purpose of thinking? What thoughts should I have?
25 Acting Rationally The Rational agent approach an agent is something that simply acts but computer agents have more then just acts that made them not just mere programsThe attributes of a agent areOperating under autonomous ( self ruling) controlIdentifying their environmentContinuing over a prolonged time periodAdjusting to changeCapable of taking on another goalA rational agent acts to get best outcome and under uncertainty the best expected outcome.
26 Acting rationally: rational agent Rational behavior: doing the right thingThe right thing: that which is expected to maximize goal achievement, given the available informationDoesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the service of rational action
27 Rational agentA rational agent acts to get best outcome and under uncertainty the best expected outcome.In the law of thought approach to AI the importance is given on correct conclusions or outcomesMaking correct conclusions or inferences are a part of being rational agent.So one way to act rationally is to reason logicallyIt has to reason logically for the given conclusions and show that the action taken will get us the desired goalRationality is not only about correct conclusions at times there is no correct thing to do yet something is to be done,For example reflex action , if I take time in thinking weather to move my hand from the stove or not then it will be to late ,At this time some action needs to be taken that’s it
28 Rational agents An agent is an entity that perceives and acts This course is about designing rational agentsAbstractly, 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 performanceCaveat: computational limitations make perfect rationality unachievable design best program for given machine resources
29 Rational agent involves the Turing test skills The rational agent approach takes all the skills needed for the Turing Test to allow these rational actions to come into beingWe need the Knowledge and reason as this helps us in taking good decisions in a variety of situations ,We need natural language prcessor in order to help us with complex languages in this complex societyWe need visual perception to get a better action , if we see a nasty pit ahead then we can move away from it to avoid damageSo the study of AI as a rational approach is more general than the “ Law of thought approach” as correct conclusions is just one of the several tools used for achieving rationality
30 Advantages of the study of AI as Rational agent design The study of AI as a rational approach is more general than the “ Law of thought approach” as correct conclusions is just one of the several tools used for achieving rationalityThis approach is more amenable to scientific development than compared to other approaches which is based on human behavior or human thoughtAs here in this approach the standard of rationality is clearly defined and completely general.Whereas in human behavior when in complicated and unknown evolutionary process still this approach cannot produce perfection in result , as humans are still good at taking decisions in a more complex situations and even emotional one.
31 The Foundation of Artificial Intelligence Academic Disciplines of AI Philosophy Logic, methods of reasoning, mind as physical system, foundations of learning, language, rationality.Mathematics Formal representation and proof, algorithms, computation, (un)decidability, (in)tractabilityProbability/Statistics modeling uncertainty, learning from dataEconomics utility, decision theory, rational economic agentsNeuroscience neurons as information processing units.Psychology/ how do people behave, perceive, process cognitiveCognitive Science information, represent knowledge.Computer building fast computers engineeringControl theory design systems that maximize an objective function over timeLinguistics knowledge representation, grammars