Artificial Intelligence A Brief Introduction

1. aslab.org Artificial IntelligenceA Brief Introduction Ricardo Sanz May 20, 2004 autonomous systems laboratory Sanz / Artificial Intelligence: An Introduction

2. Contents • Basic Ideas • History • Technology • Robots • Agents Sanz / Artificial Intelligence: An Introduction

3. Core Ideas What is AI ? Sanz / Artificial Intelligence: An Introduction

4. What is AI? • Acting humanly: The Turing test (1950) • What do we need to pass the test • Thinking humanly: Cognitive modeling • “Think-aloud” to learn from human and recreate in computer programs (GPS) • Thinking rationally: Syllogisms, Logic • Acting rationally: A rational agent Sanz / Artificial Intelligence: An Introduction

5. Foundations of AI • Philosophy (428 B.C. - Present) – reasoning and learning • Can formal rules be used to draw valid conclusions? • How does the mental I arise from a physical brain? • Where does knowledge come from? • How does knowledge lead to action? Sanz / Artificial Intelligence: An Introduction

6. Foundations of AI • Mathematics (c. 800 - Present) - logic, probability, decision making, computation • What are the formal rules to draw conclusions? • What can be computed? • How do we reason with uncertain information? • Economics (1776-present) • How should we make decisions so as to maximize payoff? • How should we do this when others may not go along? • How should we do this when the payoff may be far in the future? Sanz / Artificial Intelligence: An Introduction

7. Foundations of AI • Neuroscience (1861-present) • How do brains process information • Psychology (1879 - Present) - investigating human mind • How do humans and animals think and act? • Computer engineering (1940 - Present) - ever improving tools • How can we build an efficient computer? Sanz / Artificial Intelligence: An Introduction

8. Foundations of AI • Control theory and Cybernetics (1948-present) • How can artifacts operate under their own control? • Linguistics (1957 - Present) - the structure and meaning of language • How does language relate to thought? Sanz / Artificial Intelligence: An Introduction

9. What is Intelligence? • Intelligence, taken as a whole, consists of the following skills: • the ability to reason • the ability to acquire and apply knowledge • the ability to manipulate and communicate ideas Sanz / Artificial Intelligence: An Introduction

10. An Intelligent Entity INTERNAL PROCESSES INPUTS Has knowledge Senses environment Has understanding/ intentionality See Hear Touch Taste Smell Can Reason Exhibits behaviour OUTPUTS Sanz / Artificial Intelligence: An Introduction

11. The Age of Intelligent Machines • 1st Industrial Revolution: the Age of Automation: Machines extend & multiply man's physical capabilities • 2nd Industrial Revolution: the Age of Info Tech: Machines extend & multiply man's mental capabilities • Knowledge Revolution?: the Age of Knowledge Technology "..working smarter, not harder." • How do we make our systems smarter? - by building in intelligence? Sanz / Artificial Intelligence: An Introduction

12. More Definitions of AI • AI is the science of making machines do things that would require intelligence if done by humansMarvin Minsky • AI is the part of computer science concerned with designing intelligent computer systemsEd Feigenbaum • Systems that can demonstrate human-like reasoning capability to enhance the quality of life and improve business competitivenessJapan-S’pore AI Centre Sanz / Artificial Intelligence: An Introduction

13. Behaviourist’s View on Intelligent Machines • Many scientists believe that only things that can be directly observed are “scientific” • Therefore if a machine behaves “as if it were intelligent” it is meaningless to argue that this is an illusion. • Turing was of this opinion and proposed the “Turing Test” • This view can be summarized as:“If it walks like a duck, quacks like a duck and looks like a duck - it is a duck” Sanz / Artificial Intelligence: An Introduction

14. Turing’s Test • In 1950 Alan Turing published his now famous paper "Computing Machinery and Intelligence." In that paper he describes a method for humans to test AI programs. • In its most basic form, a human judge sits at a computer terminal and interacts with the subject by written communication only. The judge must then decide if the subject on the other end of the computer link is a human or an AI program imitating a human. • http://www.turing.org.uk/turing/ Sanz / Artificial Intelligence: An Introduction

15. Turing’s Test - Part 1 Which one’s the man? A B Sanz / Artificial Intelligence: An Introduction

16. If the computer succeeds in fooling the judge then it has managed to exhibit a human level of intelligence in the task of pretending to be a woman, the definition of intelligence the machine has shown itself to be intelligent. Turing’s Test - Part 2 Which one’s the computer? A B Sanz / Artificial Intelligence: An Introduction

17. Some History From hype to work Sanz / Artificial Intelligence: An Introduction

18. Brief History of AI • Gestation of AI (1943 -1955) • McCulloch and Pitts’s model of artificial neurons • Minsky’s 40-neuron network • Birth of AI (1956) • A 2-month Dartmouth workshop of 10 attendees – the name of AI • Newell and Simon’ Logic Theorist • Early enthusiasm, great expectations (1952 - 1969) • GPS by Newell and Simon, Lisp by McCarthy, Blockworld by Minsky Sanz / Artificial Intelligence: An Introduction

19. Brief History of AI • AI facing reality (1966 - 1973) • Many predictions of AI coming successes • A computer would be a chess champion in 10 years (1957) • Machine translation – Syntax is not enough • Intractability of the problems attempted by AI • Knowledge-based systems (1969 - 1979) • Knowledge is power, acquiring knowledge from experts • Expert systems (MYCIN) • AI - an industry (1980 - present) • Many AI systems help companies to save money and increase productivity Sanz / Artificial Intelligence: An Introduction

20. Brief History of AI • The return of neural networks (1986 – present) • PDP books by Rumelhart and McClelland • Connectionist models vs. symbolic models • AI – a science (1987 – present) • Build on existing theories vs. propose brand new ones • Rigorous empirical experiments • Learn from data – data mining • AI – intelligent agents (1995 – present) • Working agents embedded in real environments with continuous sensory inputs • AI - conscious machines (Now !!) • Making machines that feel and and have a self Sanz / Artificial Intelligence: An Introduction

21. History of AI Degree of Motivation Dartmouth Conference Support Technology Japan 5th Generation Computer AI Winter mid-1990s mid-1980s 1948 1970s - 80s Time Sanz / Artificial Intelligence: An Introduction

22. Robots Chess-playing program Voice recognition system Speech recognition system Grammar checker Pattern recognition Medial diagnosis System malfunction rectifier Game Playing Machine Translation Resource Scheduling Expert systems (diagnosis, advisory, planning, etc) Machine learning Intelligent interfaces Examples of AI systems Sanz / Artificial Intelligence: An Introduction

23. The Robocup Competition pits robots (real and virtual) against each other in a simulated soccer tournament. The aim of the RoboCup competition is to foster an interdisciplinary approach to robotics and agent-based AI by presenting a domain that requires large-scale co-operation and coordination in a dynamic, noisy, complex environment. Common AI methods used are variants of neural networks and genetic algorithms. AI Case Study - RoboCup Sanz / Artificial Intelligence: An Introduction

24. Intelligent Technologies Resources for Sophisticated Information Processing Sanz / Artificial Intelligence: An Introduction

25. Knowledge-Based Systems (KBS) Knowledge-base editor User interface may employ: Question- and- Answer, Menu-driven, Natural language, Graphics Interface Styles Etc. General Knowledge-base Inference engine Case-specific data User Explanation subsystem Sanz / Artificial Intelligence: An Introduction

26. Plant Output Input Sensors Artificial Neural Networks • What are Artificial Neural Networks (ANNs)? • ANN or connecionist systems are systems that were developed based on the learning characteristics of biological creatures. • ANN solve problems though a process of learning and adaptation. • How are ANNs represented? Synapse Neuron Outputs Inputs Connection between neurons Sanz / Artificial Intelligence: An Introduction

27. Genetic Algorithms • We will use the processes loosely based on natural selection, crossover, and mutation to find solutions to certain problems. • GAs are adaptive (search, learning) methods based on the genetic processes of biological organisms. 1st generation of possible solutions 2nd generation of possible solutions Sanz / Artificial Intelligence: An Introduction

28. Fuzzy Logic • For systems with little complexity, hence little uncertainty, closed-form mathematical expressions provide precise description of the system. • For systems that are a little more complex, but for which significant data exists, model free methods such as artificial ANNs, provide a powerful and robust means to reduce uncertainty through learning. • For most complex systems where few numerical data exists and where only ambiguous or imprecise information may be available, fuzzy reasoning provides a way to understand system behavior. Mathematical equations Model-free Methods (e.g., ANNs) Precision in the model Fuzzy Systems Complexity (uncertainty) of the system Sanz / Artificial Intelligence: An Introduction

29. Towards intelligent machines Are we ready to build the next generation of intelligent robots? Sanz / Artificial Intelligence: An Introduction

30. Some problems remain… • Vision • Audition / speech processing • Natural language processing • Touch, smell, balance and other senses • Motor control Sanz / Artificial Intelligence: An Introduction

31. Computer Perception • Perception: provides an agent information about its environment. Generates feedback. Usually proceeds in the following steps. • Sensors: hardware that provides raw measurements of properties of the environment • Ultrasonic Sensor/Sonar: provides distance data • Light detectors: provide data about intensity of light • Camera: generates a picture of the environment • Signal processing: to process the raw sensor data in order to extract certain features, e.g., color, shape, distance, velocity, etc. • Object recognition: Combines features to form a model of an object • And so on to higher abstraction levels Sanz / Artificial Intelligence: An Introduction

32. Perception for what? • Interaction with the environment, e.g., manipulation, navigation • Process control, e.g., temperature control • Quality control, e.g., electronics inspection, mechanical parts • Diagnosis, e.g., diabetes • Restoration, of e.g., buildings • Modeling, of e.g., parts, buildings, etc. • Surveillance, banks, parking lots, etc. • … • And much, much more Sanz / Artificial Intelligence: An Introduction

33. Sample perception: Computer vision • Grab an image of the object (digitize analog signal) • Process the image (looking for certain features) • Edge detection • Region segmentation • Color analysis • Etc. • Measure properties of features or collection of features (e.g., length, angle, area, etc.) • Use some model for detection, classification etc. Sanz / Artificial Intelligence: An Introduction

34. State of the art • Can recognize faces? – yes • Can find salient targets? – sure • Can recognize people? – no problem • Can track people and analyze their activity? – yep • Can understand complex scenes? – not quite but in progress Sanz / Artificial Intelligence: An Introduction

35. Face recognition case study Sanz / Artificial Intelligence: An Introduction

36. Pedestrian recognition Sanz / Artificial Intelligence: An Introduction

37. How about other senses? • Speech recognition -- can achieve user-undependent recognition for small vocabularies and isolated words • Other senses -- overall excellent performance (e.g., using gyroscopes for sense of balance, or MEMS sensors for touch) except for olfaction and taste, which are very poorly understood in biological systems also. Sanz / Artificial Intelligence: An Introduction

38. How about actuation • Robots have been used for a long time in restricted settings (e.g., factories) and, mechanically speaking, work very well. • For operation in unconstrained environments, Biorobotics has proven a particularly active line of research: • Motivation: since animals are so good at navigating through their natural environment, let’s try to build robots that share some structural similarity with biological systems. Sanz / Artificial Intelligence: An Introduction

39. Robot examples: constrained environments Sanz / Artificial Intelligence: An Introduction

40. Towards unconstrained environments Sanz / Artificial Intelligence: An Introduction

41. They’re here … Robot lawn mowers and vacuum-cleaners are here already… Sanz / Artificial Intelligence: An Introduction

42. The time is now • It is a particularly exciting time for AI because… • CPU power is getting not a problem anymore • Many physically-capable robots are available • Some vision and other senses are partially available • Many AI algorithms for constrained environment are available • So for the first time we have all the components required to build smart robots that interact with the real world. Sanz / Artificial Intelligence: An Introduction

43. Agents Recent IA software focus Sanz / Artificial Intelligence: An Introduction

44. What is an Agent? • in general, an entity that interacts with its environment • perception through sensors • actions through effectors or actuators Sanz / Artificial Intelligence: An Introduction

45. Examples of Agents • human agent • eyes, ears, skin, taste buds, etc. for sensors • hands, fingers, legs, mouth, etc. for effectors • powered by muscles • robot • camera, infrared, bumper, etc. for sensors • grippers, wheels, lights, speakers, etc. for effectors • often powered by motors • software agent • functions as sensors • information provided as input to functions in the form of encoded bit strings or symbols • functions as effectors • results deliver the output Sanz / Artificial Intelligence: An Introduction

46. Agents and Their Actions • a rational agent does “the right thing” • the action that leads to the best outcome • problems: • what is “ the right thing” • how do you measure the “best outcome” Sanz / Artificial Intelligence: An Introduction

47. Performance of Agents • criteria for measuring the outcome and the expenses of the agent • often subjective, but should be objective • task dependent • time may be important Sanz / Artificial Intelligence: An Introduction

48. Performance Evaluation Examples • vacuum agent • A number of tiles cleaned during a certain period • based on the agent’s report, or validated by an objective authority • doesn’t consider expenses of the agent, side effects • energy, noise, loss of useful objects, damaged furniture, scratched floor • might lead to unwanted activities • agent re-cleans clean tiles, covers only part of the room, drops dirt on tiles to have more tiles to clean, etc. Sanz / Artificial Intelligence: An Introduction

49. Rational Agent considerations • performance measure for the successful completion of a task • complete perceptual history (percept sequence) • background knowledge • especially about the environment • dimensions, structure, basic “laws” • task, user, other agents • feasible actions • capabilities of the agent Sanz / Artificial Intelligence: An Introduction

50. Omniscience • a rational agent is not omniscient • it doesn’t know the actual outcome of its actions • it may not know certain aspects of its environment • rationality takes into account the limitations of the agent • percept sequence, background knowledge, feasible actions • it deals with the expected outcome of actions Sanz / Artificial Intelligence: An Introduction