![Agent function tabulation for vacuum cleaner agent
Percept Sequence Action
[A, clean] Right
[A, Dirty] Suck
[B, clean] left
Performance measure of vacuum cleaner agent
amount of dirt cleaned up
power consumption
amount of noise generated](https://image.slidesharecdn.com/module1additional2-240402180553-1283da92/85/Artificial-Intelligence-Module-1_additional2-ppt-70-320.jpg)
Artificial Intelligence Module 1_additional2.ppt
- 1. Module 1: Artificial Intelligence Introduction
- 2. Contents What is AI Why AI History of AI Applications of AI Classification of AI Agent Agent’s Environment Types of Agent
- 3. AI - Definition • Branch of computer Science • Imitate the roles of human brain Intelligence Artificial Artificial Intelligence
- 4. What’s involved in Intelligence? Ability to interact with the world (speech, vision, motion, manipulation). Ability to model the world and to reason about it. Ability to learn and to adapt.
- 5. What Is AI? Definition of AI It is a branch of computer science dedicated to create intelligent machines that work and react like humans. Artificial intelligence, as the name suggests, describes the ability of machines to imitate human mental prowess. However, this intelligence is not restricted to machines — it also applies to software systems. The three major components are, therefore, machine or system, software, and internet connectivity (cloud and big data).
- 6. Definition of AI It is a branch of computer science which deals with helping machines finds solutions to complex problems in a more human like fashion. This generally involve borrowing characteristics from human intelligence and applying them as algorithms in a computer friendly way
- 7. In simple, AI is design of intelligence in an artificial device- McCarthy John McCarthy is one of the "founding fathers" of artificial intelligence, together with Alan Turing, Marvin Minsky, Allen Newell, and Herbert A. Simon.
- 8. Ai- Improvements AI Decision making Increased accuracy Solve complex problems
- 9. 1 2 3 4 Perceives its environment Takes actions to achieve goals Revolves around the use of algorithms Mimic functions of human brain AI- working
- 11. A Brief History of AI
- 12. A Brief History of AI In 1946, John Mauchly and Pres Eckert unveiled their own digital computer, called ENIAC, which was programmable and which was actually used, for computing projectile ballistics and then for designing the hydrogen bomb. They were finally awarded a patent in 1964.
- 13. A Brief History of AI Cntd… 1943: McCulloch and Pitts propose a model of artificial neurons 1956 Minsky and Edmonds build first neural network computer, the SNARC -Minsky is the one who opposed Rosenblat’s Perceptron
- 14. The Dartmouth Conference (1956) John McCarthy organizes a two-month workshop for researchers interested in neural networks and the study of intelligence Agreement to adopt a new name for this field of study: Artificial Intelligence A Brief History of AI Cntd…
- 15. A Brief History of AI Cntd… In 1958
- 16. A Brief History of AI Cntd… In 1963
- 17. 1952-1972 Enthusiasm: Arthur Samuel’s checkers player Shakey the robot Lots of work on neural networks A Brief History of AI Cntd…
- 18. 1966-1974 Reality: AI problems appear to be too big and complex Computers are very slow, very expensive, and have very little memory (compared to today) A Brief History of AI Cntd…
- 19. 1969-1979 Knowledge-based systems: Birth of expert systems Idea is to give AI systems lots of information to start with A Brief History of AI Cntd…
- 20. A Brief History of AI Cntd… In 1970
- 21. A Brief History of AI Cntd… In 1972
- 22. 1990s to the present: Increases in computational power (computers are cheaper, faster, and have tons more memory than they used to) An example of the coolness of speed: Computer Chess
- 23. Computer Chess 2/1996: Kasparov vs Deep Blue Kasparov victorious: 3 wins, 2 draws, 1 loss 3/1997: Kasparov vs Deeper Blue First match won against world champion How do you think it works???
- 24. Deeper Blue - 512 processors: 200 million chess positions per second
- 25. AI - History
- 33. Applications - AI AI have placed its foot in all the fields • Engineering Science • Health Care • Banking Sector • Metrology • Education • Business • Hospitality Industry • Behavioral Sciences • Tourism • Legal Law • Agriculture • Fashion Technology
- 34. AI – Trans-disciplinary Engineering No more Computer science, electrical, Mechanical, civil engineers. • Humanoid robots - Sophia • Smart Home Automation (Appliances) • Automatic cars/ Driverless cars • Smart Green Houses • 3-D Houses • Flight Simulations
- 49. Human Intelligence Vs Artificial Intelligence
- 52. Cyborg In a typical example, a human with an artificial cardiac pacemaker or implantable cardioverter-defibrillator would be considered a cyborg, since these devices measure voltage potentials in the body, perform signal processing, and can deliver electrical stimuli, using this synthetic feedback mechanism to keep that person alive.
- 53. AI- Methods Symbolic • Knowledge base systems • Rule based systems Computational Intelligence • Neural Networks • Fuzzy logic • Evolutionary Algorithms
- 54. Four categories of AI System that think like human -cognitive modeling System that think rationally -laws of thought System that act like human -turing test System that act rationally -rational agents Human vs rational approach or study of computation Thought process vs behavior approach Human centered approach involves hypothesis and experimental confirmation Rational approach involves mathematics and engineering.
- 55. Turing Test : Mr. Alan Turing one of the famous computer scientists proposed the Turing Test in the year 1950. He proposed that: Turing test is used to determine “whether or not machines can think intelligently like humans?" The basic configuration of Turing test is: There will be a human interrogator on one side of the wall and the other side a machine and a human. The interrogator is going to ask a question via teletype; both the machine and human present on the other side will answer to the question via teletype. The interrogator should be able distinguish between the machine and human responses. If he can not be able to distinguish (the answers provided by the machine or the human) then the machine passes the test and the machine is considered as intelligent (or thinking intelligently like humans).
- 56. AI types
- 57. Strong AI Weak AI Criteria based AI
- 58. Ability based AI Narrow AI • Dedicated to one task General AI • Performs like human Super AI • Intelligent than human
- 59. Functionality based AI Self aware – Systems will have emotions and desires of their own Theory of mind - understands emotions, needs and thoughts Limited – Learn from history eg: driverless cars Reactive- oldest AI and “ Doesn’t learn” eg: IBM deep blue
- 60. Motivation of AI
- 61. Motivation of AI
- 63. AI- Statistics for 2020
- 64. Tools
- 65. Agents An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators Human agent: eyes, ears, and other organs for sensors; hands, legs, mouth, and other body parts for actuators Robotic agent: cameras and infrared range finders for sensors and Wheels, lights, speakers for actuators
- 67. Agents Operate in an environment. An agent perceives its environment using sensors. An agent can change the environment using actuators. Have goals.
- 68. Autonomous agent The agent which decides autonomously which action to take in the current situation to maximize progress towards its goal. Performance measure An objective criterion for success of an agent’s behavior.
- 69. Example: Vacuum-cleaner world It has only two locations. The vacuum cleaner agent perceives which location it is in and whether there is dirt or not. Based on that it can choose to move left, right, suck up the dirt or do nothing.
- 70. Agent function tabulation for vacuum cleaner agent Percept Sequence Action [A, clean] Right [A, Dirty] Suck [B, clean] left Performance measure of vacuum cleaner agent amount of dirt cleaned up power consumption amount of noise generated
- 71. Intelligent Agent Must sense Must act Must be autonomous Must be rational
- 72. Rational Agent AI is about building rational agent. An agent should strive to "do the right thing", based on what it can perceive and the actions it can perform. The right action is the one that will cause the agent to be most successful. Rational Agent: For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure.
- 73. PEAS PEAS: Performance measure, Environment, Actuators, Sensors i) Consider, e.g., the task of designing an automated taxi driver as agent: PEAS description: Performance measure: Safe, fast, legal, comfortable trip, maximize profits Environment: Roads, other traffic, pedestrians, customers Actuators: Steering wheel, accelerator, brake, signal, horn Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard
- 74. ii) Agent: Medical diagnosis system Performance measure: Healthy patient, minimize costs, lawsuits Environment: Patient, hospital, staff Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) Sensors: Keyboard (entry of symptoms, findings, patient's answers)
- 75. Agent Environment Environment in which agents operate can be defined in different ways
- 76. Fully observable (vs. partially observable): An agent's sensors give it access to the complete state of the environment at each point in time. Eg. Vacuum agent Deterministic (vs. stochastic): The next state of the environment is completely determined by the current state and the action executed by the agent. If the environment is partially observable then it is stochastic.
- 77. Episodic (vs. sequential): The agent's experience is divided into atomic "episodes" (each episode consists of the agent perceiving and then performing a single action), and the choice of action in each episode depends only on the episode itself. Static (vs. dynamic): The environment is unchanged while an agent is deliberating. Discrete (vs. continuous): A limited number of distinct, clearly defined percepts and actions. Single agent (vs. multiagent): An agent operating by itself in an environment.
- 80. Example: If car infront is braking then initiate braking
- 82. It keep track of the current state of the world using an internal model. It then chooses an action. Ex. Changing the lane while driving
- 84. It keep track of the current state of the world as well as set of goals it is trying to achieve and chooses an action that will lead to the achievement of goal. Ex. Taxi at a junction to reach the destination
- 86. Goal alone is not enough to get the high quality behavior in most environment. Goal and utility are necessary.. Ex. Taxi to reach destination quickly, safely, cheaper than other
- 88. Learning Agents Learning element for making improvement. Performance element for selecting external actions.
Editor's Notes
- #12: This is ABC Machine from 1942…. Atanasoff was in fact the first computer scientist, since he and a student, Clifford Berry, built a digital computer at Iowa State in the late 1930s. It was not programmable, and although it was designed to solve simultaneous linear equations, they didn’t really put it to use. But it had most of the features of a modern digital computer, including a refreshable memory (made, interestingly, of capacitors arranged around a drum). Atanasoff, however, was pulled into other projects during World War II and never patented his invention.
- #13: It turns out that Mauchly had seen Atanasoff’s computer in 1941 and had spent considerable time discussing computing prospects with Atanasoff. Atanasoff never complained about not receiving any credit (or a share of the patent)
- #15: Participants: Marvin Minsky, Allen Newel, Herbert A Simon etc.
- #16: By John McCarthy
- #20: Expert System is an interactive and reliable computer-based decision-making system which uses both facts and heuristics to solve complex decision-making problems. It is considered at the highest level of human intelligence and expertise. The purpose of an expert system is to solve the most complex issues in a specific domain.
- #21: Following are the Expert System Examples: MYCIN: It was based on backward chaining and could identify various bacteria that could cause acute infections. It could also recommend drugs based on the patient’s weight. It is one of the best Expert System Example. DENDRAL: Expert system used for chemical analysis to predict molecular structure. PXDES: An Example of Expert System used to predict the degree and type of lung cancer CaDet: One of the best Expert System Example that can identify cancer at early stages