Artificial intelligence & neural networks

1. Artificial intelligence & neural networks Introduction Cybernetics Research Lab GC University Lahore Wajahat M. Qazi Deputy Director Department of Computer Science, GC University Lahore

2. Two main goals of AI: • To understand human intelligence better. We test theories of human intelligence by writing programs which emulate it. • To create useful “smart” programs able to do tasks that would normally require a human expert. Why do AI?

3. Dijkstra The question of whether a computer can think is no more interesting than the question of whether a submarine can swim.

4. A very general mental capability that, among other things, involves the ability to reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience. It is not merely book learning, a narrow academic skill, or test-taking smarts. Rather, it reflects a broader and deeper capability for comprehending our surroundings — catching on, making sense of things, or figuring outwhat to do. Mainstream Science on Intelligence (1994), A report by fifty-two researchers • But the big feature of human-level intelligence is not what it does when it works but what it does when it's stuck. Marvin Minsky Intelligence

5. Human artifacts that replicates or simulate a real thing • Genuine physical phenomenon reproduced using human made device What is Artificial?

6. Implementation of Computer Programs for effectively modeling THOUGHT, LEARNING, CATEGORIZATION, REASONING, MEMORY, COMPARISIONandLANGUAGE • Branch of Computer Science that is concern with the AUTOMATION OF INTELLIGENT BEHAVIOUR What is Artificial Intelligence?

7. Learning, Knowledge, Reason, Adaptive, Evolvable, Fault-tolerance, Memorization, Plan, Manipulate Objects, Perception, Consciousness, self-awareness, Natural Language Processing, Creativity, Social Intelligence, Collaborate, negotiate, classify, recognize, Uncertainty and Reasoning with incomplete information with belief … • Act or Think Humanly • Act or Think Rationally Artificial Intelligence

8. Weak A.I. • Assumes that computer is treated as a powerful tool to study mind. • Strong A.I (Artificial General Intelligence). • Assumes that computer “really is a mind” if appropriately programmed Artificial Intelligence

9. Neat A.I. • Scurfy A.I. School of Thoughts

10. Fixed Control architecture • Learning architecture • Ontogenetic architecture Taxonomy of Rob-/Soft- bots

11. Cybernetics and brain simulation • GOFAI • Cognitive Simulation • Neat/Logical AI • Scruffy/Symbolic AI • Knowledge based AI • Sub-symbolic AI • Computational Intelligence/Soft Computing • Bottom-up, embodied, situated, behavior-based or nouvelle AI , Granular Computing, Evolutionary Computing, Artificial Intelligence. • Formalization (Mathematics. Economics and OR) • Intelligent Agents Paradigm/Distributed AI • Quantum (Machine/Artificial) Intelligence • Artificial Life • Hard Life • Soft Life • Wet Life Approaches to A.I.

12. A.I and Cybernetics both have influenced the area of Machine Intelligence. • The difference between A.I. and Cybernetics lies in the way they treat Knowledge. • A.I. presumes that Knowledge can be stored inside a machine and its applications to the real world constitute intelligence. • Whereas Cybernetics treats knowledge from constructivist view of the world and intelligence is characteristic of an interaction and cannot be stored Artificial Intelligence and Cybernetics

13. Thinking Humanly • Acting Humanly • Thinking Rationally • Acting Rationally What is A.I.

14. Turing (1950) "Computing machinery and intelligence": • "Can machines think?"  "Can machines behave intelligently?" • Operational test for intelligent behavior: the Imitation Game • Predicted that by 2000, a machine might have a 30% chance of fooling a lay person for 5 minutes • Anticipated all major arguments against AI in following 50 years • Suggested major components of AI: knowledge, reasoning, language understanding, learning Acting humanly: Turing Test

15. What is intelligence? • Can a machine be truly “intelligent”? Is there more to human intelligence than rules, data and calculations? Tests: • Turing Test: 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? • Can Humans also qualify the Turing Test? If not then does it means that Humans are not Intelligent. Philosophical Issues

16. 1960s "cognitive revolution": information-processing psychology • Requires scientific theories of internal activities of the brain • -- How to validate? Requires 1) 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 Thinking humanly: cognitive modeling

17. Rational behavior: doing the right thing • The right thing: that which is expected to maximize goal achievement, given the available information • Doesn't necessarily involve thinking – e.g., blinking reflex – but thinking should be in the service of rational action Acting rationally: rational agent

18. 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; • various motors for actuators Intelligent Agents

19. The agentfunction maps from percept histories to actions: [f: P* A] • The agentprogram runs on the physical architecture to produce f • agent = architecture + program Intelligent Agents

20. Percepts: location and contents, e.g., [A,Dirty] • Actions: Left, Right, Suck, NoOp Example

21. Rationality is distinct from omniscience (all-knowing with infinite knowledge) • Agents can perform actions in order to modify future percepts so as to obtain useful information (information gathering, exploration) • An agent is autonomous if its behavior is determined by its own experience (with ability to learn and adapt) Rational Agent

22. PEAS: Performance measure, Environment, Actuators, Sensors • Must first specify the setting for intelligent agent design • Consider, e.g., the task of designing an automated taxi driver: • Performance measure Environment • Actuators • Sensors PEAS

23. Must first specify the setting for intelligent agent design • Consider, e.g., the task of designing an automated taxi driver: • 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 PEAS

24. 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) PEAS

25. Agent: Part-picking robot • Performance measure: Percentage of parts in correct bins • Environment: Conveyor belt with parts, bins • Actuators: Jointed arm and hand • Sensors: Camera, joint angle sensors PEAS

26. Agent: Interactive English tutor • Performance measure: Maximize student's score on test • Environment: Set of students • Actuators: Screen display (exercises, suggestions, corrections) • Sensors: Keyboard PEAS

27. Four basic types in order of increasing generality: • Simple reflex agents • Model-based reflex agents • Goal-based agents • Utility-based agents • Learning Agents Agent Types

28. Simple Reflex Agent

29. Model-based Agents

30. Goal-based Agents

31. Utility Agent

32. Learning Agent

33. Fully observable (vs. partially observable): An agent's sensors give it access to the complete state of the environment at each point in time. • 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 deterministic except for the actions of other agents, then the environment is strategic) • 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. Environment Type

34. Static (vs. dynamic): The environment is unchanged while an agent is deliberating. (The environment is semidynamic if the environment itself does not change with the passage of time but the agent's performance score does) • 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. Environment Type