1 / 46

Introduction to Artificial Intelligence Prof. Dr. Ir. Widodo Budiharto 2019

Course : Artificial Intelligence. Introduction to Artificial Intelligence Prof. Dr. Ir. Widodo Budiharto 2019. Father of AI. "The Dartmouth summer research project on artificial intelligence”. Jhon McCarthy, The father of AI. Artificial Intelligence. Artificial intelligence  ( AI ).

deec
Download Presentation

Introduction to Artificial Intelligence Prof. Dr. Ir. Widodo Budiharto 2019

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Course : Artificial Intelligence Introduction to Artificial IntelligenceProf. Dr. Ir. Widodo Budiharto 2019

  2. Father of AI • "The Dartmouth summer research project on artificial intelligence” Jhon McCarthy, The father of AI T0264 - Artificial Intelligence

  3. Artificial Intelligence Artificial intelligence (AI) the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages

  4. What is AI? Thinking Humanly “The exciting new effort to make computers thinks … machine with minds, in the full and literal sense” (Haugeland, 1985) Thinking Rationally “The study of mental faculties through the use of computational models” (Charniak and McDermott, 1985) Acting Humanly “The study of how to make computers do things at which, at the moment, people are better” (Rich and Knight, 1991) Acting Rationally “Computational Intelligence is the study of the design of intelligent agents” (Poole et al., 1998)

  5. Acting humanly The Turing Test (Alan Turing, 1950) Instead of duplicating an exemplar, it is more useful and important to study the principles of the intelligence

  6. Thinking humanly • The cognitive modelling • Part of cognitive science • Once we have a sufficiently precise theory of the mind, it becomes possible to express the theory as a computer program

  7. Thinking rationally • The “laws of thought” or logic • Aristotle was one of the first to introduce logic or “right thinking” • Syllogisms provided patterns for argument structure • Correct premises = correct solutions • Example: • He is a boy; All boys are handsome; • Therefore, he is handsome

  8. Acting rationally • Rational behavior: doing the right thing • The right thing: that which is expected to maximize goal achievement given the available information • Example: • Given money Rp. 100.000, you have to buy a birthday gift • Which one will you choose? Which one is more rational? • Bracelet (Rp. 100.000) or Ring (Rp. 150.000)

  9. Rational Agent • An agent • Just something that acts • A rational agent • One that acts as to achieve the best (expected) outcome • The rational-agent approach has two advantages: • It is more general than the “laws of thought” approach • it is more amenable to scientific development

  10. Demo Robot EdukasiEduRobot

  11. AI Applications [source] • Speech Recognition • Virtual Assistants • Siri (Apple) • Google Now • Cortana (Microsoft) • They helps us to arrange meetings, check weather, do a phone call, send a message, etc.

  12. AI Applications [source] • Machine Translation • Google Translate • No more bringing dictionary when travelling

  13. AI Applications • Robotics • Several robots were sent to Fukushima nuclear tragedy to perform various tasks (Left) • Hubo: A KAIST Robot who wins the DARPA Robot Challenge (Right) [source] [source]

  14. AI Applications • Recommendation Systems • AI helps to provide items / photos / various things based on our social activities • Instagram Explore / Search Feed • If we follow many badminton accounts, they show:

  15. AI Applications • Search Engines • Google’s search engines algorithm is designed to show internet pages of our interests in a blink of eyes

  16. AI Applications • Sender: • asdadsa@asda.com • sdajhda@afasa.com • asdjhaksdah@asffa.com • Title: • Hi, I need your help! • 1 million dollar for you now! • [blank] • Content: • Congrats, you won XXX Awards. Please tell me your name, address, birth date, and telephone number to xxx_awards@gmail.com • Email • Spam/Junk email detection

  17. AI Applications [source] Face Detection

  18. AI Applications • Face Recognition • China’s facial recognition technology to identify the citizen [source]

  19. AI Applications • Games • Chess (1997): Kasparov vs. IBM Deep Blue • Powerful search algorithms • Jeopardy! (2011): Humans vs. IBM Watson • Natural language processing and information extraction • Go (2016): Lee Sedol vs. Google AlphaGo • Deep learning + reinforcement learning + search algorithms! • Future: 5 vs 5 AI for Dota

  20. AI Applications [source] [source] • Games • March 2016, AlphaGo beat Lee Sedol (4 vs 1) • December 2016, AlphaGo beat KeJie (3 vs 0)

  21. AI Applications [source] • Autonomous Driving • NuTonomy: A robo-taxi service in Singapore

  22. AI Applications [source] • Autonomous Driving • Waymo: An autonomous car company under Alphabet, Inc. (Google’s parent company)

  23. Foundation of AI

  24. Foundation of AI • Philosophy • Logic, methods of reasoning • Foundations of learning, language, rationality • Mathematics • Logic: Formal representation and proof • Algorithms, computation, (un)decidability, (in)tractability • Probability

  25. Foundation of AI • Economics • Formal theory of rational decisions • Neuroscience • Plastic physical substrate for mental activity • Psychology • Adaptation • Phenomena of perception and motor control • Experimental techniques (psychophysics, etc.)

  26. Foundation of AI • Computer Engineering • How can we build an efficient computer to build AI program? • Control Theory and Cybernetics • Simple optimal agent designs • Linguistics • Knowledge representation • Grammar

  27. Brief History of AI

  28. Agent An agentis anything that can be viewed as perceiving its environmentthrough sensorsand acting upon that environment through actuators.

  29. Agent A vacuum-cleaner world with just two locations Percept: location and contents, i.e. [A, Dirty] Actions: Left, Right, Suck, NoOp

  30. Agent Partial tabulation of the simple agent function

  31. Concept of Rationality 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.

  32. Task Environments To build a rational agent, we need to first define the PEAS: P (Performance) E (Environment) A (Actuators) S(Sensors)

  33. What is PEAS for? [source] • Autonomous car • Performance: safety, destination, legality, comfort • Environment: streets, pedestrian, highway, weather • Actuators: steering, accelerator, brake, horn • Sensors: video, GPS, accelerometer, keyboard

  34. Structure of Intelligent Agents Program • Agent = Architecture + Program • Architecture is the hardware • Sensors + Actuators • Program is the software

  35. Agent Types Four basic type of agents: Simple reflex agents Modal-based reflex agents Goal-based agents Utility-based agents All of which can be generalized into learning agents that can improve their performance and generate better actions.

  36. Simple Reflex Agents An action is done based on the current state only. Ignore the sensors history.

  37. Modal-based Reflex Agents The sensors and actions history is used to model the world / environment. An action is done based on the world model.

  38. Goals-based Agents An action is done based on the combined information from the world model and goal information.

  39. Utility-based Agents An action is done based on the agent happiness (utility). It is the agent’s performance measure.

  40. Learning Agents Programming agents by hand can be very tedious. Some more expeditious method seem desirable" Alan Turing, 1950.

  41. Expert Systems

  42. Presentation Topics (1 group : 4-5 persons, 50 minutes) • Searching methods (principles, algorithm and demo in C#/Python) • First Order Logic and Inference in First Order Logic • Computer Vision ( principles and Demo in OpenCV) • Robotics and Robot Vision (Simple Demo using Arduino Codes/OpenCV) • Machine Learning k-NN and SVM (Simple Demo using C#/Python) • Reasoning with Uncertainty (principles and algorithm and demo in C#/Python) • Knowledge representation and Planning and Acting in the Real World • Fuzzy Logic (principles and demo in C#/Python) • Neural Networks and Deep learning (principles and demo in C#) • Bayesian & Probabilistic Reasoning Over Time ( principles and demo in C#) • Making simple and complex decisions (principles and demo in C#) • Natural Language Processing Starting at the second week, create the power point presentation,summary in Ms Word and demo code send to prof.Widodo.Budiharto@gmail.com. T0264 - Artificial Intelligence

  43. Project Presentation on Session 25-26Kelompok 4-5 orang/grup BuatAplikasi AI yang bergunamenggunakan Python, Arduino, OpenCV atau mobile apps. Dapatdigunakanuntuklomba PKM-KC dandikembangkanuntukSkripsi. Dipresentasikanmenggunakan ppt secarakelompok di pertemuan 12-13 Softcopy Laporanberbentuk paper 5-8 halamandengannama yang lengkapdapatdikirimkeprof.Widodo.Budiharto@gmail.com

  44. Homework Explain the definition of AI Create a program using Python for displaying image import numpy as np import cv2 # Load an color image in grayscale img = cv2.imread('messi5.jpg',0) cv2.imshow('image',img) cv2.waitKey(0) cv2.destroyAllWindows()

  45. KelompokPresentasi(7 orang/kelompok)sertakan demo Program Search Strategies, Local Search and Adversarial Search Logical Agents and First Order Logic Fuzzy Systems and Implementation Computer Vision, Robot and Robot Vision Natural Language Processing Quantifying Uncertainty Machine Learning and Big Data Probabilistic Reasoning and Probabilistic Reasoning over Time Artificial Neural Network dan Deep Learning K-NN dan SVM Learning Probabilistic Models

  46. References https://simpleai.readthedocs.io/en/latest/search_problems.html Widodo Budiharto and Derwin Suhartono (2015), Artificial Intelligence, Andi offset Publisher. Stuart Russell, Peter Norvig. 2010. Artificial Intelligence : A Modern Approach. Pearson Education. New Jersey. ISBN:9780132071482

More Related