[OR]



UNIT - IIntroduction: A.I, History of A.I, The state of the Art, Intelligent Agents: Agents and Environments, Good behavior, The nature of Environments, the Structure of Agents.1. Introduction:We call ourselves Homo sapiens-man the wise- because our mental capacities are so important to us. For thousands of years, we have tried to understand how we think; that is, how a mere handful of stuff can perceive, understand, predict, and manipulate a world far larger and more complicated that itself. The field of artificial intelligence, or AI, pursues creating the computers or machines as intelligent as human beings.Human Intelligence(Brain)Artificial Intelligence(Machine)Human intelligence is analogue as work in the form of signalsArtificial intelligence is digital, they majorly works in the form of numbersHumans uses their schema and content memoryIt is using the built in, designed by scientist memoryHuman brain does have bodyTheir brain is no bodyHuman intelligence is biggerArtificial intelligence is little and temporaryHuman intelligence is reliableArtificial intelligence is notNo hardware/softwareHardware/softwareHumans have feelings and emotions, and they can express these emotions.Machines have no feelings and emotions. They just work as per the details fed into their mechanical brain.Humans have the capability to understand situations, and behave accordingly.Machines do not have this capability.While humans behave as per their consciousness.Machines just perform as they are taught.What is AI:According to the father of Artificial Intelligence John McCarthy, it is “The science and engineering of making intelligent machines, especially intelligent computer programs”. Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a software think intelligently, in the similar manner the intelligent humans think. AI is accomplished by studying how human brain thinks and how humans learn, decide, and work while trying to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and systems.Definitions of artificial intelligence according to eight textbooks are shown in fig:Systems that think like humansSystems that think rationally(logically)“The exciting new effort to make computers think….machines with minds, in the full and literal sense”“[The automation of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning…”“ The study of mental faculties through the use of computational models”“The study of the computations that make it possible to perceive, reason, and act”Systems that act like humansSystems that act rationally“The art of creating machines that perform functions that require intelligence when performed by people”“The study of how to make computers do things at which, at the moment, people are better”“Computational Intelligence is the study of the design of intelligent agents”“AI is concerned with intelligent behavior in artifacts.” Views of AI fall into four categories: 1.Thinking humanly 2.Thinking rationally 3.Acting humanly 4.Acting rationallyActing humanly: The Turing Test approach: To conduct this test, we need two people and the machine to be evaluated. One person plays the role of the interrogator, who is in a separate room from the compute and the other person. The interrogator can ask questions of either the person or the computer by typing questions and receiving typed responses. However, the interrogator knows them only as A and B and aims to determine which the person is and which are the machine. The goal of the machine is to fool the interrogator into believing that is the person. If the machine succeeds at this, then we will conclude that the machine is acting humanly. But programming a computer to pass the test provides plenty to work on, to posses the following capabilities. Thinking Humanly: The Cognitive modeling approach: To construct a machine program to think like a human, first it requires the knowledge about the actual workings of human mind. After completing the study about human mind it is possible to express the theory as a computer program. It the program‘s input/output and timing behavior matches with the human behavior then we can say that the program‘s mechanism is working like a human mind. Example: General Problem Solver (GPS) Thinking rationally: The laws of thought approach: The right thinking introduced the concept of logic. Example: Ram is a student of III year CSE. All students are good in III year in CSE. Ram is a good student Acting rationally: Acting rationally means, to achieve one‘s goal given one‘s beliefs. In the previous topic laws of thought approach, correct inference is selected, conclusion is derived, but the agent acts on the conclusion defined the task of acting rationally.Applications of AI AI has been dominant in various fields such as: Gaming AI plays crucial role in strategic games such as chess, poker, tic-tac-toe, etc., where machine can think of large number of possible positions based on heuristic knowledge. Natural Language Processing It is possible to interact with the computer that understands natural language spoken by humans. Expert Systems There are some applications which integrate machine, software, and special information to impart reasoning and advising. They provide explanation and advice to the users. Vision Systems These systems understand, interpret, and comprehend visual input on the computer. For example,A spying aeroplane takes photographs which are used to figure out spatial information or map of the areas. Doctors use clinical expert system to diagnose the patient.Police use computer software that can recognize the face of criminal with the stored portrait made Speech Recognition Some intelligent systems are capable of hearing and comprehending the language in terms of sentences and their meanings while a human talks to it. It can handle different accents, slang words, noise in the background, change in human’s noise due to cold, etc. Handwriting Recognition The handwriting recognition software reads the text written on paper by a pen or on screen by a stylus. It can recognize the shapes of the letters and convert it into editable text. Intelligent Robots Robots are able to perform the tasks given by a human. They have sensors to detect physical data from the real world such as light, heat, temperature, movement, sound, bump, and pressure. They have efficient processors, multiple sensors and huge memory, to exhibit intelligence. In addition, they are capable of learning from their mistakes and they can adapt to the new environment. by forensic artist.Applications of Artificial IntelligenceDetails of following Applications 1.Finance 2.Medical 3.Industries 4.Telephone maintenance 5.Telecom 6.Transport 7.Entertainment 8.Pattern Recognition 9.Robotics 10.Data Mining2. History of AIHere is the history of AI during 20th century:3. The state of the Art (Applications of AI)Here we sample a few applications:Autonomous planning and scheduling: A hundred million miles from Earth, NASA’s Remote Agent program became the first on-board autonomous planning program to control the scheduling of operations for a spacecraft. Remote Agent generated plans from high-level goals specified from the ground, and it monitored the operation of the spacecrafts as the plans were executed—detecting, diagnosing and recovering from problems as they occurred.Game playing:IBM’s deep blue became the first computer program to defeat the world champion in a chess match when it bested Garry Kasparov by score of 3.5 to 2.5 in an exhibition match. Kasparov said that he felt a “new kind of intelligence” across the board from him. Newsweek magazine described the match as “The brain’s last stand.” The value of IBM’s stock increased by $18billion.Autonomous control:The ALVINN computer vision system was trained to steer a car to keep it following a lane. It was placed in CMU’s NAVLAB computer controlled minivan vehicle 98% of the time. A human took over the other 2, mostly at exit ramps. NAVLAB has video cameras that transmit road images to ALVINN, which then computes the best direction to steer, based on experience from previous training runs.Diagnosis:Medical diagnosis programs based on probabilistic analysis have been able to perform at the level of an expert physician in several areas of medicine. Heckerman(1991) describes a case where a leading expert on lymph-node pathology scoffs at a program’s diagnosis of an especially difficult case. The creators of the program suggest he ask the computer for an explanation of the diagnosis. The machine points out the major factors influencing its decision and explains the subtle interaction of several of the symptoms in this case. Eventually, the expert agrees with the program.Logistics Planning:During the 1991 gulf war, U.S. forces deployed an ( Dynamic Analysis and Replanning Tool, DART) AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people.Robotics:Many surgeons now use robot assistants in microsurgery. HipNav(1996) is a system that uses computer vision techniques to create a three-dimensional model of a patient’s internal anatomy and then uses robotic to guide the insertion of a hip replacement prosthesis.Language understanding and problem solving:PROVERB is a computer program that solves crossword puzzles better than most humans. [OR]3. Applications of AIAI is used in applicable in many aspects such as Finance, Medical, Transport, Entertainment, Pattern recognition, Data mining and many more. Some important applications of AI are listed below:1. GamingAI plays an important role in designing strategic games such as chess, tic-tac-toe etc. These are the logical games in which the system can determine the various available options based on the information fed.?2. Natural Language Processing (NLP)It is possible to interact with the computer that understands human language.3. Expert SystemExpert systems are developed to solve complex problems by the knowledge of reasoning, which is represented primarily using if–then rules rather than conventional procedural code.?4. Vision SystemComputer Vision system is a technology of obtaining models to control information from visual data.For example:Police use computer software that can recognize the face of the criminal with the stored portrait made by forensic artist.5. RobotsRobots are able to perform the tasks given by humans.4. Intelligent AgentsIntroduction:An intelligent agent (or simply an?agent) is a type of software application that searches, retrieves and presents information from the Internet. This application automates the process of extracting data from the Internet, such as information selected based on a predefined criterion, keywords or any specified information/entity to be searched. Intelligent agents are often used as Web browsers, news retrieval services and online shopping. An intelligent agent may also be called an agent or bot.1. Agents and Environments:An agent is anything that can be perceives its environment through sensors and acting upon that environment through effectors.A human agent has sensory organs such as eyes, ears, nose, tongue and skin parallel to the sensors, and other organs such as hands, legs, mouth, for effectors. A robotic agent replaces cameras and infrared range finders for the sensors, and various motors and actuators for effectors. A software agent has encoded bit strings as its programs and actions.Agent TerminologyPerformance Measure of Agent?? It is the criteria, which determines how successful an agent is.Behaviour of Agent?? It is the action that agent performs after any given sequence of percepts.Percept?? It is agent’s perceptual inputs at a given instance.Percept Sequence?? It is the history of all that an agent has perceived till date.Agent Function?? It is a map from the precept sequence to an action.Example: The vacuum-cleaner world shown in fig: This particular world has just two locations: square A and B.Imagine that our intelligent agent is a robot vacuum cleaner. Let’s suppose that the world has just two rooms. Percepts: location and contentsEx: [A, Dirty]Actions: Left, Right, Suck, NoOpGoal formulation: Intuitively, we want all the dirt cleaned up. Formally, the goal is {state 7, state 8 }.One very simple agent function is the following:Function REFLEX-VACUUM-AGENT ([location, status]) returns actionIf status=Dirty then return Suckelse if location=A the return Rightelse if location=B then return LeftState Space Graph:Percept SequenceAction[A, Clean]Right[A, Dirty]Suck[B, Clean]Left[B, Dirty]Suck[A, Clean], [A, Clean]Right[A, Clean], [A, Dirty]SuckMeasuring performanceWith any intelligent agent, we want it to find a (good) solution and not spend forever doing it.The interesting quantities are, therefore,the?search cost--how long the agent takes to come up with the solution to the problem, andthe?path cost--how expensive the actions in the solution are.The?total cost?of the solution is the sum of the above two quantities.2. Good behavior (The concept of Rationality)Rational Agent: An agent that does the “right” thing.Every entry in the table for the agent function is filled out correctly.Doing the right thing is better than doing the wrong thing.Performance MeasureA scoring function for evaluating the environment spaceRational Agent – for each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, given the evidence provided by the percept sequence and whatever built-in knowledge the agent has.RationalityWhat is rational at any given time depends on four things:1. The performance measure that defines the criterion of success.2. The agent's prior knowledge of the environment.3. The actions that the agent can perform.4. The agent's percept sequence to date.This leads to a definition of a rational agent:For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, given the evidence provided by the percept sequence and whatever built-in knowledge the agent has.3. The nature of EnvironmentsSpecifying the task environmentThe rationality of the simple vacuum-cleaner agent, needs specification of the performance measure, the environment, the agent’s actuators and sensors. We will group all these together under the heading of the task environment. We call this the PEAS (Performance, Environment, Actuators, Sensors) description. In designing an agent, the first step must always be to specify the task environment as fully as possible.Let us consider a more complex problem: an automated taxi driver.Agent TypePerformance MeasureEnvironmentActuatorsSensorsTaxi DriverSafe: fast, legal, comfortable trip,maximize profitsRoads, other traffic,pedestrians, customersSteering, accelerator,brake, signal,horn, displayCameras, sonar,speedometer,GPS, odometer, accelerometer,engine sensors,key boardTable: PEAS description of the task environment for an automated taxi.Agent TypePerformance MeasureEnvironmentActuatorsSensorsMedicaldiagnosis systemHealthy patient, minimize costs, lawsuitsPatient, hospital,staffDisplayquestions, tests,diagnoses,treatments,referralsKeyboard entry of symptoms, findings, patient's answersSatellite imageanalysis systemCorrect imagecategorizationDownlink fromorbiting satelliteDisplaycategorization of sceneColor pixel arraysPart-pickingrobotPercentage ofparts in correctbinsConveyor beltwith parts; binsJointed arm and handCamera, joint angle sensorsRefinerycontrollerMaximize purity, yield, safetyRefinery, operatorsValves, pumps, heaters, displaysTemperature, pressure, chemical sensorsInteractiveEnglish tutorMaximizestudent's scoreon testSet of students, testing agencyDisplay exercises, suggestions,correctionsKeyboard entryTable: Examples of agent types and their PEAS descriptions.Properties of task Environments:The environment has multi fold properties ?Discrete / Continuous?? If there are a limited number of distinct, clearly defined, states of the environment, the environment is discrete (For example, chess); otherwise it is continuous (For example, driving).Observable / Partially Observable?? If it is possible to determine the complete state of the environment at each time point from the percept’s it is observable; otherwise it is only partially observable.Static / Dynamic?? If the environment does not change while an agent is acting, then it is static; otherwise it is dynamic.Single agent / Multiple agents?? The environment may contain other agents which may be of the same or different kind as that of the agent.Accessible / Inaccessible?? If the agent’s sensory apparatus can have access to the complete state of the environment, then the environment is accessible to that agent.Deterministic / Non-deterministic?? If the next state of the environment is completely determined by the current state and the actions of the agent, then the environment is deterministic; otherwise it is non-deterministic.Episodic / Non-episodic?? In an episodic environment, each episode consists of the agent perceiving and then acting. The quality of its action depends just on the episode itself. Subsequent episodes do not depend on the actions in the previous episodes. Episodic environments are much simpler because the agent does not need to think ahead. 4. The Structure of Agents:Agent’s structure can be viewed as ?Agent = Architecture + Agent ProgramArchitecture = the machinery that an agent executes on.Agent Program = an implementation of an agent function.Agent FunctionAgent ProgramAn abstract mathematical descriptionA concrete implementation, running on the agent architecture.They take the entire percept history.They take the current percept as input from the sensors and return an action to the actuators.Agent programsThe agent programs all have the same skeleton: they take the current percept as input from the sensors and return an action to the actuators.Example 1:Agent: Intelligent house Percepts: signals from temperature sensor, movement sensor, clock, sound sensor Actions: room heaters on/off, lights on/off Goals: occupants warm, rooms light when occupied, house energy efficient Environment: at various times, occupants enter and leave house, enter and leave rooms; daily variation in outside light and temperatureExample 2:Agent: Car driver Percepts: camera (array of pixels of various intensities), signals from GPS, speedometer, sonar Actions: steer, accelerate, and brake Goals: safe, fast, legal trip Environment: streets, intersections, traffic signals, traffic lights, other moving vehicles, pedestriansWe outline four basic kinds of agent program that embody the principles underlying almost all intelligent systems:Simple reflex agentsModel-based reflex agentsGoal-based agentsUtility-based agents1. Simple Reflex Agents:They choose actions only based on the current percept.They are rational only if a correct decision is made only on the basis of current precept.Their environment is completely observable.Reflex agents respond immediately to percepts.Condition-Action Rule?? It is a rule that maps a state (condition) to an action.This agent selects actions based on the agent’s current perception or the world and not based on past perceptions.Example 1: If a mars Lander found a rock in a specific place it needed to collect then it would collect it, if it was a simple reflex agent then if it found the same rock in a different place it would still pick it up as it doesn't take into account that it already picked it up.Example 2: Our brain pulls our hand away without thinking about any possibility that there could be danger in the path of your arm. We call these reflex actions. This kind of connection where only one possibility is acted upon is called a condition-action rule, written as:if?hand is in fire?then?pull away handExample 3: Imagine yourself as the driver of the automated taxi. If the car in front brakes and its brake lights come on, then you should notice this and initiate braking. We call such a connection a condition-action rule: Written as if car-in-front-is-braking then initiate –braking.The simple reflex agent has a library of such rules so that if a certain situation should arise and it is in the set of Condition-action rules the agent will know how to react with minimal reasoning.CharacteristicsOnly works if the environment is fully observable.Lacking(Missing) history, easily get stuck in infinite loopsOne solution is to randomize actionsAdvantages: – Easy to implement – Uses much less memory than the table-driven agent Disadvantages: – Will only work correctly if the environment is fully observable – Infinite loops2. Model-based reflex agents: A model-based agent can handle a partially observable environment. Its current state is stored in the agent maintaining some kind of structure which describes the part of the world which cannot be seen. This knowledge about “how the world evolves” is called a model of the world, hence the name “model-based agent”Maintain some internal state that keeps track of the part of the world it can’t see now Needs model (encodes knowledge about how the world works)Example 1: A Match refereePercept:Points won by teamMisconductTimersActions:Announce points won by teamGive warnings/yellow/red cardReview communications between team and third umpiresCondition-action rule:If player(s) kick another player then misconductIf misconduct level 1 then warningIf misconduct level 2 then yellow cardIf misconduct level 3 then red card3. Goal-based agents (Problem-Solving Agent):The current state of the environment is not always enough to decide what to do. For example, at a road junction, the taxi can turn left, turn right, or go straight on. The correct decision depends on where the taxi is trying to get to.Goal?? It is the description of desirable situations.Reflex agents respond immediately to percepts.The goal should be known to the agent by means of a sequence of actions necessary to follow during operation.Goal-based agents further expand on the capabilities of the model-based agents, by using “goal” information. It allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state.Example 1 :?The destination should be known to a taxi driver so that the available routes can be derived.?Example 2: at a road junction, the taxi can turn left, turn right, or go straight on. The correct decision depends on where the taxi is trying to get to.Example ProblemsVacuum worldInitial state:Our vacuum can be in any state of the 8 states shown in the picture.State description:Successor function generates legal states resulting from applying the three actions {Left, Right, and Suck}.The states space is shown in the picture, there are 8 world states.Goal test:Checks whether all squares are clean.Path cost:Each step costs 1, so the path cost is the sum of steps in the path.Example 2:8-puzzleInitial state:Our board can be in any state resulting from making it in any configuration.State description:Successor function generates legal states resulting from applying the three actions {move blank Up, Down, Left, or Right}.State description specifies the location of each of the eight titles and the blank.Goal test:Checks whether the states matches the goal configured in the goal state shown in the picture.Path cost:Each step costs 1, so the path cost is the sum of steps in the path.4. Utility-based agents (Distinguish between Different goals):Using the utility-based agent it can measure which direction might be better to get to the destination.Utility-based agents try to maximize their own "happiness."The goal should be achieved with some performance measure set by the user.The cost, degree of comfort and safety are associated with achievement of specific goals.The right decision= Function (percept, goal) +quicker+ safer + reliable+ Less costGoal Based AgentUtility Based AgentGoal-based and utility-based agents can select an action to attain a desired outcome.The utility-based agent compares the utilities of different possible outcomes, and selects the action that causes the outcome with the highest utility.The medial prefrontal cortex is involved in implementing the goal-based action selection.The striatum is involved in implementing the utility-based action bias.This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state.A more general performance measure should allow a comparison of different world states according to exactly how happy they would make the agent. The term utility can be used to describe how “happy” the agent is. ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download