10072937

Introduction to Artificial Intelligence Naoufel Werghi Khalifa University Naoufel Werghi Introduction to Artificial Intelligence Naoufel Werghi PROFESSOR, DEPARTMENT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Habilitation and...

Introduction to Artificial Intelligence Naoufel Werghi Khalifa University Naoufel Werghi Introduction to Artificial Intelligence Naoufel Werghi PROFESSOR, DEPARTMENT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Habilitation and Ph.D. in Computer Vision from the University of Strasbourg. Worked in University of Edinburgh, University of Glasgow Leader of the Artificial Intelligence and Big Data Theme in the Cyber-Physical Security System Center (C2PS) Project leader in Khalifa University Center for Autonomous Robotic System (KUCARS). Research interests: Computer vision and machine learning Leading several funded projects related to biometrics, medical imaging, remote sensing, surveillance, and intelligent systems. 23 research grants and published more than 200 journal and conference papers.. Naoufel Werghi Introduction to Artificial Intelligence Course outline Artificial Intelligence : Introduction Classic Artificial Intelligence Search techniques Modern Artificial Intelligence Classification & Machine learning Naoufel Werghi Introduction to Artificial Intelligence From the film “2001 Space Odyssey”, released 1969 Naoufel Werghi Introduction to Artificial Intelligence From the film “2001 Space Odyssey” This famous scene shows a dialogue between the astronaut and HAL 9000, a machine controlling the systems on board of the spacecraft. In this scene, HAL 9000 seems not obeying the instructions Questions? 1- What type of human intelligence Hall 9000 seems possessing 2- Do you think HAL 9000 is taking control of itself ? Self-control Taking actions that he was not suppose to do Naoufel Werghi Introduction to Artificial Intelligence What is AI? “The study of the computations that make it possible to perceive, reason, and act" (Winston, 1992) Naoufel Werghi Introduction to Artificial Intelligence What is AI? (Cont.) Discipline that systematizes and automates intellectual tasks to create machines that act like humans or think like humans Act like humans Act rationally Think like humans Think rationally Naoufel Werghi Introduction to Artificial Intelligence 1. Act like humans AI is the art of creating machines that perform functions that require intelligence when performed by humans Methodology: Take an intellectual task at which people are better and make a computer do it Naoufel Werghi Introduction to Artificial Intelligence 1. Act like humans: Examples Prove a theorem Naoufel Werghi Introduction to Artificial Intelligence 1. Act like humans: Examples Play chess Naoufel Werghi Introduction to Artificial Intelligence 1. Act like humans: Examples Diagnose a disease Naoufel Werghi Introduction to Artificial Intelligence 1. Act like humans: Examples Driving a car Naoufel Werghi Introduction to Artificial Intelligence The Turing Test Alan Turing (1950) "Computing machinery and Intelligence" "Can machines think? Can machines behave intelligently?" Operational test for intelligent behavior: the Imitation Game Naoufel Werghi Introduction Artificial Intelligence to Artificial – Introduction Slide 1 Intelligence The Turing Test (Cont.) Hidden room Interrogator Naoufel Werghi Introduction Artificial Intelligence to Artificial – Introduction Slide 1 Intelligence The Turing Test (Cont.) Hidden room Interrogator Naoufel Werghi Introduction Artificial Intelligence to Artificial – Introduction Slide 1 Intelligence The Turing Test (Cont.) Hidden room Interrogator Naoufel Werghi Introduction Artificial Intelligence to Artificial – Introduction Slide 1 Intelligence The Turing Test (Cont.) Gives an objective notion of intelligence and avoids the inevitable debates over the true nature of intelligence Avoids the unanswerable questions as whether or not the computer uses the appropriate internal processes Focuses solely on the content of the answers to questions and avoids the question of (living organisms / machine intelligence) Naoufel Werghi Introduction Artificial Intelligence to Artificial – Introduction Slide 1 Intelligence 2. Think Like Humans How the computer performs functions does matter Understand the traces of the reasoning steps Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans How the computer performs functions does matter Understand the traces of the reasoning steps Cognitive science : Testable theories of the workings of the human mind Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Aristotle's syllogism: Patterns for arguments structure that always gave correct conclusions from correct premises Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Aristotle's syllogism: Patterns for arguments structure that always gave correct conclusions from correct premises Modus Ponens Rule : A→ B is true ; A→ B means A is true ; If A is true then B is true Then B is true Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact: true) Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Find the basic statements Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Find the basic statements Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) A 1.If it is raining, B is wet. (Always true) then the ground 2.is raining. A ( Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) rainin → 1. it is A B is true 2. raining. A (. is true Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Modus Ponens Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Modus Ponens Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Modus B is true Ponens Naoufel Werghi Introduction to Artificial Intelligence 2. Think Like Humans Using the Modus Ponens Rule to analyze and draw conclusion from this piece of information 1.If it is raining, then the ground is wet. (Always true) 2.It is raining. (Known fact) Modus The ground Ponens is wet Naoufel Werghi Introduction to Artificial Intelligence Major AI Techniques Logic Search Machin learning Reasoning, Knowledge if-then rules 32 Naoufel Werghi Introduction to Artificial Intelligence AI History 1943: McCulloch & Pitts Publish the First Mathematical Model of a Neural Network Naoufel Werghi Introduction to Artificial Intelligence AI History 1950: Alain Truring : The Turing test Human evaluator engages in conversation with a machine Naoufel Werghi Introduction to Artificial Intelligence AI History 1956: The term “Artificial Intelligence” was coined Dartmrouth workshop Naoufel Werghi Introduction to Artificial Intelligence AI History 1957: Rosenblatt develops the Perceptron The first artificial neural network capable of learning. Naoufel Werghi Introduction to Artificial Intelligence AI History 1965-1967 Weizenbaum develops ELIZA: a natural language processing program Newell and Simon develop the General Problem Solver (GPS) programs to demonstrate human-like problem-solving Naoufel Werghi Introduction to Artificial Intelligence AI History 1980: Expert systems: Financial forecasting and medical diagnoses. Naoufel Werghi Introduction to Artificial Intelligence AI History 1986: Hinton, Rumelhart, and Williams publish “Learning Representations by Back- Propagating Errors” → deeper neural networks to be trained. Naoufel Werghi Introduction to Artificial Intelligence AI History 1997: IBM’s DeepBlue defeats Chess Champion Kasparov Naoufel Werghi Introduction to Artificial Intelligence AI History 2012: Deep learning era AlexNet: Early “deep learning system” a many-leayer neural network system capbale of recognizing 1000 objects suchs dogs and cars at near-human level. Naoufel Werghi Introduction to Artificial Intelligence AI History 2014: Facebook Deepface: a facial recognition system That can recognize faces with near-human accuracy: Naoufel Werghi Introduction to Artificial Intelligence AI History 2014: Facebook Deepface: a facial recognition system That can recognize faces with near-human accuracy: Naoufel Werghi Introduction to Artificial Intelligence AI History 2017: Ashish Waswani published “Attention Is All You Need” New deep learning architecture for natural language processing Naoufel Werghi Introduction to Artificial Intelligence AI History 2017: Ashish Waswani et al published “Attention Is All You Need” New deep learning architecture for natural language processing Naoufel Werghi Introduction to Artificial Intelligence AI History 2020: OpenAI releases ChatGPT Significant breakthrough in natural language processing, Naoufel Werghi Introduction to Artificial Intelligence  Artificial Intelligence In Khalifa University Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Face-Recognition Applications Surveillance and Security Gateless ticketing Medical : Down Syndrome Diagnosis Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Tissue phenotyping for colorectal cancer detection and prognosis Nucleus Detection and Classification from WSI using Graphs and Deep CNNS Nucleus Detection and Classification from WSI using Graphs and Deep CNNS Input tile Nucleus Detection & Cell Graph of cancer cells (400 x 400) Classification Tumor Epithelial Cell Normal Epithelial Cell Lymphocytes Cell Spindle-shaped Cell Necrotic Cell 49 Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Automtatic screeening of passenger baggage Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Automtatic screeening of passenger baggage Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Automtaic vision-based flare monitoring Naoufel Werghi Introduction to Artificial Intelligence Artificial Intelligence In Khalifa University Predicitive maintenance Failure Crack detection, debris removal, leaks, corrosion Assets Sensors Network Image, s Video - - Prevention Multi-modal Physical models Hisytory Ground-truth data Naoufel Werghi Introduction to Artificial Intelligence Thank you Naoufel Werghi Introduction to Artificial Intelligence