1- Introduction to A I and systems pptx

AI

1. Introducing Artificial intelligence Dr Eid Emary 1

2. Agenda / Topics What about the course Project Methodology Key Findings/Results Research drilldown Conclusion 2

3. What about the course ? TM358 is the code for the module Machine learning and artificial intelligence. It is a level 3 course with 8 credit hours This module aims to provide an introduction to the basic principles, techniques, and applications of Artificial Intelligence. Coverage includes symbolic AI, game playing, planning, optimization and neural networks basics. The assessments of this module is divided as MTA (30), TMA(15), contribution (5) and final (50). 3

4. What about the course ? By the end of the course you will be able to: Define the aims and motivations for AI. Discover AI concepts and terms like machine learning, neural networks and deep learning. Recognize issues and concerns surrounding AI such as ethics and bias, & jobs. Recite key concepts and methods in evolutionary computation. Distinguish the different Cognitive Computing phases (Perception, Learning, Reasoning) Associate the different AI primitives to different AI applications. Select and use appropriate mathematical representations for a range of problem solving systems; Compare, contrast and evaluate competing approaches to computational problem solving and the simulation of intelligence; 4

5. What about the course ? By the end of the course you will be able to: Construct different preprocessing primitives for different AI applications Apply different methods for classification and regression using traditional AI methods Experiment with different tools for decision support and planning Choose among the different models hyper parameters according to the application and analysis of results. Measure the different performance indicators for individual AI systems. Rank the different AI methods Adapt individual Method according to the problem in hand. Assemble different methods for creating appropriate AI pipeline. 5

6. What about the course ? The module content will be: Week 1 What is AI? Applications and Examples of AI, AI Concepts, Terminology, and Application Areas Week 2 AI: Issues, Concerns and Ethical Considerations, The Future with AI, and AI in Action Week 3 Basics of symbolic AI, Search Week 4 Basics of symbolic AI, Planning and game playing - introducing STRIPS language or other replacements such as Prolog Week 5 Basics of symbolic AI, Planning and game playing -STRIPS language or other languages such as Prolog, Week 6 Evolutionary computation principles and methods – adopting optimization libraries in python such as PYSwarm or scipy Week 7 Evolutionary computation methods and applications – adopting optimization libraries in python such as PYSwarm or scipy Week 8 Evolutionary computation advanced applications – adopting optimization libraries in python such as PYSwarm or scipy Week 9 Neural Networks Basics, architectures – adopting Keras libraries in python Week 10 Neural Networks architectures and training – adopting Keras libraries in python Week 11 Practical applications of neural networks – adopting Keras libraries in python Week 12 Introduction to robotics and reinforcement learning – adopting reinforcement libraries in python such as KerasRL 6

7. What about the course ? Key reading list: Stuart Russell, Peter Norvig , 2016, Artificial intelligence A modern approach Pearson https://online.stanford.edu/courses/xcs221-artificial-intelligence-principles-and-techniques https://openai.com/ https://www.visual-prolog.com/ 7

8. What is Artificial Intelligence ? making computers that think? the automation of activities we associate with human thinking, like decision making, learning ... ? the art of creating machines that perform functions that require intelligence when performed by people ? the study of mental faculties through the use of computational models ? the study of computations that make it possible to perceive, reason and act ? a field of study that seeks to explain and emulate intelligent behaviour in terms of computational processes ? a branch of computer science that is concerned with the automation of intelligent behaviour ? anything in Computing Science that we don't yet know how to do properly ? (!) 8

9. What is Artificial Intelligence ? 9 Systems that act rationally Systems that think like humans Systems that think rationally Systems that act like humans THOUGHT BEHAVIOUR HUMAN RATIONAL

10. Systems that act like humans: Turing Test “The art of creating machines that perform functions that require intelligence when performed by people.” (Kurzweil) “The study of how to make computers do things at which, at the moment, people are better.” (Rich and Knight) 10

11. Systems that act like humans: Turing Test You enter a room which has a computer terminal. You have a fixed period of time to type what you want into the terminal, and study the replies. At the other end of the line is either a human being or a computer system. If it is a computer system, and at the end of the period you cannot reliably determine whether it is a system or a human, then the system is deemed to be intelligent. 11

12. Systems that act like humans: The Turing Test approach a human questioner cannot tell if there is a computer or a human answering his question, via teletype (remote communication) The computer must behave intelligently Intelligent behavior to achieve human-level performance in all cognitive tasks 12

13. Systems that act like humans: These cognitive tasks include: Natural language processing for communication with human Knowledge representation to store information effectively & efficiently Automated reasoning to retrieve & answer questions using the stored information Machine learning to adapt to new circumstances 13

14. What is Artificial Intelligence ? 14 Systems that act rationally Systems that think like humans Systems that think rationally Systems that act like humans THOUGHT BEHAVIOUR HUMAN RATIONAL

15. Systems that think like humans: cognitive modeling Humans as observed from ‘inside’ How do we know how humans think? Introspection vs. psychological experiments Cognitive Science “The exciting new effort to make computers think … machines with minds in the full and literal sense” ( Haugeland ) “[The automation of] activities that we associate with human thinking, activities such as decision-making, problem solving, learning …” (Bellman) 15

16. What is Artificial Intelligence ? 16 Systems that act rationally Systems that think like humans Systems that think rationally Systems that act like humans THOUGHT BEHAVIOUR HUMAN RATIONAL

17. Systems that think ‘rationally’ "laws of thought" Humans are not always ‘rational’ Rational - defined in terms of logic? Logic can’t express everything (e.g. uncertainty) Logical approach is often not feasible in terms of computation time (needs ‘guidance’) “The study of mental facilities through the use of computational models” ( Charniak and McDermott) “The study of the computations that make it possible to perceive, reason, and act” (Winston) 17

18. What is Artificial Intelligence ? 18 Systems that act rationally Systems that think like humans Systems that think rationally Systems that act like humans THOUGHT BEHAVIOUR HUMAN RATIONAL

19. Systems that act rationally: “ Rational agent” Rational behavior: doing the right thing The right thing: that which is expected to maximize goal achievement, given the available information Giving answers to questions is ‘acting’. I don't care whether a system: replicates human thought processes makes the same decisions as humans uses purely logical reasoning 19

20. Systems that act rationally Logic  only part of a rational agent, not all of rationality Sometimes logic cannot reason a correct conclusion At that time, some specific (in domain) human knowledge or information is used Thus, it covers more generally different situations of problems Compensate the incorrectly reasoned conclusion 20

21. Systems that act rationally Study AI as rational agent – 2 advantages: It is more general than using logic only Because: LOGIC + Domain knowledge It allows extension of the approach with more scientific methodologies 21

22. Rational agents An agent is an entity that perceives and acts This course is about designing rational agents Abstractly, 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 performance Caveat: computational limitations make perfect rationality unachievable  design best program for given machine resources 22

23. AI- high level view Artificial Produced by human art or effort, rather than originating naturally. Intelligence is the ability to acquire knowledge and use it" [ Pigford and Baur ] So AI was defined as: AI is the study of ideas that enable computers to be intelligent. AI is the part of computer science concerned with design of computer systems that exhibit human intelligence (From the Concise Oxford Dictionary) 23

24. Goals of AI To make computers more useful by letting them take over dangerous or tedious tasks from human Understand principles of human intelligence 24

25. Areas of AI and Some Dependencies 25 Search Vision Planning Machine Learning Knowledge Representation Logic Expert Systems Robotics NLP

26. Advantages of AI more powerful and more useful computers new and improved interfaces solving new problems better handling of information relieves information overload conversion of information into knowledge 26

27. Disadvantages of AI increased costs difficulty with software development - slow and expensive few experienced programmers few practical products have reached the market as yet. 27

28. Search Search is the fundamental technique of AI. Possible answers, decisions or courses of action are structured into an abstract space, which we then search. Search is either "blind" or “uninformed": blind we move through the space without worrying about what is coming next, but recognising the answer if we see it informed we guess what is ahead, and use that information to decide where to look next. We may want to search for the first answer that satisfies our goal, or we may want to keep searching until we find the best answer . 28

29. Knowledge Representation & Reasoning The second most important concept in AI If we are going to act rationally in our environment, then we must have some way of describing that environment and drawing inferences from that representation. how do we describe what we know about the world ? how do we describe it concisely ? how do we describe it so that we can get hold of the right piece of knowledge when we need it ? how do we generate new pieces of knowledge ? how do we deal with uncertain knowledge ? 29

30. Knowledge Declarative knowledge deals with factoid questions (what is the capital of India? Etc.) Procedural knowledge deals with “How” Procedural knowledge can be embedded in declarative knowledge 30 Knowledge Declarative Procedural

31. planning Given a set of goals, construct a sequence of actions that achieves those goals: often very large search space but most parts of the world are independent of most other parts often start with goals and connect them to actions no necessary connection between order of planning and order of execution what happens if the world changes as we execute the plan and/or our actions don’t produce the expected results? 31

32. Learning If a system is going to act truly appropriately, then it must be able to change its actions in the light of experience: how do we generate new facts from old ? how do we generate new concepts ? how do we learn to distinguish different situations in new environments ? 32

33. Intelligent behavior In order to enable intelligent behaviour, we will have to interact with our environment. Properly intelligent systems may be expected to: accept sensory input vision, sound, … interact with humans understand language, recognise speech, generate text, speech and graphics, … modify the environment robotics 33

34. Symbolic and Sub-symbolic AI Symbolic AI is concerned with describing and manipulating our knowledge of the world as explicit symbols, where these symbols have clear relationships to entities in the real world. Sub-symbolic AI (e.g. neural-nets) is more concerned with obtaining the correct response to an input stimulus without ‘looking inside the box’ to see if parts of the mechanism can be associated with discrete real world objects. 34

35. AI applications Medicine : Image guided surgery 35 Autonomous Planning & Scheduling: Autonomous rovers.

36. AI applications Games 36 Other application areas: Bioinformatics: Gene expression data analysis Prediction of protein structure Text classification, document sorting: Web pages, e-mails Articles in the news Video, image classification Music composition, picture drawing Natural Language Processing . Perception.

37. Agents 37

38. 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; various motors for actuators 38

39. Agents and environments The agent function maps from percept histories to actions: [ f : P*  A ] The agent program runs on the physical architecture to produce f agent = architecture + program 39

40. Vacuum-cleaner world Percepts: location and contents, e.g., [ A,Dirty ] Actions: Left , Right , Suck , NoOp 40

41. Rational agents 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 Performance measure: An objective criterion for success of an agent's behavior E.g., performance measure of a vacuum-cleaner agent could be amount of dirt cleaned up, amount of time taken, amount of electricity consumed, amount of noise generated, etc. 41

42. Rational agents 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. 42

43. What’s involved in Intelligent agents? Ability to interact with the real world to perceive, understand, and act e.g., speech recognition and understanding and synthesis e.g., image understanding e.g., ability to take actions, have an effect Knowledge Representation, Reasoning and Planning modeling the external world, given input solving new problems, planning and making decisions ability to deal with unexpected problems, uncertainties Learning and Adaptation we are continuously learning and adapting our internal models are always being “updated” e.g. a baby learning to categorize and recognize animals 43

44. A vacuum cleaner agent 44

45. Rational agent design 45

46. Robots as an example of intelligent agents 46

47. Robot architecture Robots are physical agents that perform tasks by manipulating the physical world. Robots are equipped with effectors such as legs, wheels, joints, and grippers. Effectors have a single purpose: to assert physical forces on the environment. Robots are also equipped with sensors , which allow them to perceive their environment. Present day robotics employs a diverse set of sensors, including cameras and lasers to measure the environment, and gyroscopes and accelerometers to measure the robot’s own motion. 47

48. Robot main categories Most of today’s robots fall into one of three primary categories. Manipulators mobile robot mobile manipulator 48

49. Manipulators Manipulators , or robot arms are physically anchored to their workplace, for example in a factory assembly line or on the International Space Station. Manipulator motion usually involves a chain of controllable joints, enabling such robots to place their effectors in any position within the workplace. Manipulators are by far the most common type of industrial robots, with approximately one million units installed worldwide. Some mobile manipulators are used in hospitals to assist surgeons. Few car manufacturers could survive without robotic manipulators, and some manipulators have even been used to generate original artwork. 49

50. Mobile robot Mobile robots move about their environment using wheels, legs, or similar mechanisms. They have been put to use delivering food in hospitals, moving containers at loading docks, and similar tasks. The planetary rover shown explored Mars for a period of 3 months in 1997. 50 Other types of mobile robots UAV include unmanned air vehicles (UAVs), commonly used for surveillance, crop-spraying, and military operations.

51. Mobile manipulator combines mobility with manipulation Humanoid robots mimic the human torso. Mobile manipulators can apply their effectors further afield than anchored manipulators can, but their task is made harder because they don’t have the rigidity that the anchor provides. 51

52. Real robots Real robots must cope with environments that are partially observable, stochastic , dynamic , and continuous . Many robot environments are sequential and multiagent as well. Partial observability and stochasticity are the result of dealing with a large, complex world. Robot cameras cannot see around corners, and motion commands are subject to uncertainty due to gears slipping, friction, etc. 52

53. Robot hardware -sensors Sensors are the perceptual interface between robot and environment Passive sensors , such as cameras , are true observers of the environment: they capture signals that are generated by other sources in the environment. Active sensors , such as sonar , send energy into the environment. They rely on the fact that this energy is reflected back to the sensor . Active sensors tend to provide more information than passive sensors , but at the expense of increased power consumption and with a danger of interference when multiple active sensors are used at the same time. 53

54. Robot hardware -sensors Range finders are sensors that measure the distance to nearby objects. Sonar sensors emit directional sound waves, which are reflected by objects, with some of the sound making it back into the sensor. The time and intensity of the returning signal indicates the distance to nearby objects. tactile sensors such as whiskers, bump panels, and touch-sensitive skin . These sensors measure range based on physical contact, and can be deployed only for sensing objects very close to the robot. 54

55. Robot hardware -sensors Location sensors use range sensing as a primary component to determine location. Outdoors, the Global Positioning System (GPS) is the most common solution to the localization problem. GPS measures the distance to satellites that emit pulsed signals . Differential GPS involves a second ground receiver with known location, providing millimeter accuracy under ideal conditions. Unfortunately, GPS does not work indoors or underwater. 55

56. Robot hardware -sensors proprioceptive sensors , which inform the robot of its own motion . To measure the exact configuration of a robotic joint, motors are often equipped with shaft decoders that count the revolution of motors in small increments. On robot arms, shaft decoders can provide accurate information over any period of time. On mobile robots, shaft decoders that report wheel revolutions can be used for odometry —the measurement of distance traveled. Unfortunately, wheels tend to drift and slip, so odometry is accurate only over short distances. 56

57. Robot hardware -effectors Effectors are the means by which robots move and change the shape of their bodies. We count one degree of freedom for each independent direction in which a robot, or one of its effectors, can move. For example, a rigid mobile robot such as an AUV has six degrees of freedom, three for its (x, y, z) location in space and three for its angular orientation, known as yaw , roll , and pitch . These six degrees define the kinematic state or pose of the robot. The dynamic state of a robot includes these six plus an additional six dimensions for the rate of change of each kinematic dimension, that is, their velocities. 57