Artificial Intelligence: Course Outline and Introduction

ARTIFICIAL INTELLIGEN CE DR. SAMIA  COURSE DESCRIPTION This course provides students with the main fundamentals of Artificial Intelligence (AI). The course covers the main techniques that are used in AI examples (from chess-playing to self- driving cars). These techniques include sear...

ARTIFICIAL INTELLIGEN CE DR. SAMIA  COURSE DESCRIPTION This course provides students with the main fundamentals of Artificial Intelligence (AI). The course covers the main techniques that are used in AI examples (from chess-playing to self- driving cars). These techniques include search algorithms, probability, reasoning and inference, programming logic, expert systems, rule-based systems, fuzzy logic, machine learning, knowledge representation, pattern recognition, and natural language processing. The course helps students to use AI to solve specific problems in their future careers. The theoretical part of the course focuses on understanding concepts, structures, and algorithms, while the practical part (lab) includes a set of exercises to be performed using AI tools such as python. TEXTBOOKS Michael Negnevitsky, Artificial Intelligence: Intelligent Systems Approach, 3/E, ISBN: 9781408225745, 2011. Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Global Edition 3/E, ISBN: 9781292153964, 2017. Alberto Artasanchez; Prateek Joshi, Artificial Intelligence with Python: Your complete guide to building intelligent apps using Python 3.x and TensorFlow 2, 2nd Edition, ISBN 9781839219535, Publisher: Packt Publishing, Published: January 2020. TOPICS Introduction: What is AI?  State of the art of AI Intelligent Agents (chapter2 from Modern Approach book) Problem Solving and Search Algorithms (chapter3-and-4 from Modern Approach book) - Breadth-first search - Uniform-cost search - Depth-first search - Depth-limited search - Iterative deepening search - Best-first search -A* search - Heuristics TOPICS (CONT’D) Game Playing (chapter6 from Modern Approach book). MinMax Algorithm. Rule-based expert systems (Chapter 02 from Intelligent Systems Approach book). Fuzzy expert systems (Chapter 04 and Chapter 05 from Intelligent Systems Approach book). Artificial neural networks (Chapter 07, 08 – Artificial Neural Networks). Evolutionary computation (Chapter 09 – Evolutionary Computation – Genetic Algorithms). Hybrid intelligent systems. Natural Language Processing. Grading Assignments, Activities, Project, and Quizzes 40% Mid term 20% Final Exam 40% Lec. 1 Outline What is AI? Relationship of AI, Machine Learning, and Deep Learning Three Major Schools of Thought AI Technologies and Types AI Trends and Applications Artificial Intelligence (AI) AI in the Society’s Eyes People get to know AI through news, movies, and actual applications in daily life. ►News ►AI applications ►AI industry outlook ►Challenges faced by AI... ►Movies ►AI control over human beings ►Self-awareness of AI... ►Applications in daily life ►Security protection ►Entertainment ►Smart home ►Finance. Dartmouth Workshop: AI Birth In August 1956, some scientists and mathematicians gathered at Dartmouth College, discussing about how to make machines simulate human learning and any other feature of intelligence. The workshop ran for two months. No consensus was reached, but they picked the name artificial intelligence for the field they discussed about. Then, the year 1956 marked the birth of AI. AI in the Researchers’ Eyes Alan Turing (1950): I propose to consider the question, ’Can machines think?’ John McCarthy (1956): The branch of computer science concerned with making computers behave like humans. Marvin Minsky: The science of making machines do things that would require intelligence if done by men.  What is AI?  AI is a technical science that studies and develops theories, methods, technologies, and applications for simulating and extending human intelligence.  The purpose of AI is to enable machines to think like people and to make machines intelligent.  Today, AI has become an interdisciplinary course that involves various fields. What is AI? (cont’d) AI Definition: Turing Test Relationship of AI, Machine Learning (ML), and Deep Learning (DL) Relationship of AI, ML, and DL (cont’d) ►AI: A new technical science that focuses on the research and development of theories, methods, techniques, and application systems for simulating and extending human intelligence. ►ML: A core research field of AI. It focuses on the study of how computers can obtain new knowledge or skills by simulating or performing learning behavior of human beings, and reorganize existing knowledge architecture to improve its performance. ►DL: A new field of ML. The concept of DL originates from the research on artificial neural networks. DL aims to simulate the human brain to interpret data such as images, sounds, and texts. AI Development History Outline What is AI? Relationship of AI, Machine Learning, and Deep Learning Three Major Schools of Thought AI Technologies and Types AI Trends and Applications Three Major Schools of Thought What is AI? - Symbolicism - Connectionism. - Actionism Symbolicism ►Principle: Physical symbol system hypothesis and finite reasonableness principle. ►Origin: Mathematical logic. ►Concept: ►Symbol is the human cognition unit, and the cognition process is a symbol operation process. ►People are regarded as a physical symbol system, so are computers. Therefore, computers can be used to simulate human behavior. ►Knowledge is a form of information and is the basis of intelligence. The critical issues of AI are knowledge representation and knowledge inference. Symbolicism (cont’d) Connectionism ►Principle: Neural network, connection mechanism and learning algorithm between neural networks. ►Origin: bionics, especially the study of the human brain model. ►Concept: ►Neuron, instead of the symbol operation process, is the basic thinking unit. ►Human brain differs from computers, and the human brain pattern can be used to replace the computer pattern. Connectionism (cont’d) Actionism Principle: cybernetics and perception-action control system. Origin: Cybernetics. Concept: Intelligence depends on perception and actions. Intelligence requires no knowledge, representation, and inference. Actionism (cont’d) Mainstream AI Theories Mainstream AI Theories (cont’d) Outline What is AI? Relationship of AI, Machine Learning, and Deep Learning Three Major Schools of Thought AI Technologies and Types AI Trends and Applications Overview of AI Technologies ►AI technologies are multi-layered, covering the application, algorithm mechanism, tool chain, device, chip, process, and material layers. AI Types Intelligent Robots Classification ►Thinking like human beings: weak AI, such as Watson and AlphaGo. ►Acting like human beings: weak AI, such as humanoid robot, iRobot, and Atlas of Boston Dynamics. ►Thinking rationally: strong AI (Currently, no intelligent robots of this type have been created due to the bottleneck in brain science.) ►Acting rationally: strong AI. Outline What is AI? Relationship of AI, Machine Learning, and Deep Learning Three Major Schools of Thought AI Technologies and Types AI Trends and Applications AI Applications AI Applications (cont’d) Speech Signal Processing Computer Vision Natural Language Processing Machine Learning Type of AI: - 3 types of AI Any questions?