Artificial Intelligence Principles of AI PDF

Course Name: Principles of Artificial Intelligence Course Code: 0142231 Chapter One: Introduction to AI  The birth of AI is in 1956. AI is a subfield of computer science that is concerned with how What is computer programs/ machines can think and act l...

Course Name: Principles of Artificial Intelligence Course Code: 0142231 Chapter One: Introduction to AI  The birth of AI is in 1956. AI is a subfield of computer science that is concerned with how What is computer programs/ machines can think and act like human. AI refers to the simulation of human intelligence in machines Artificial that are programmed to think like humans and mimic their actions. Intelligence AI is concerned with the automation of activities that we (AI)? associate with human thinking, like decision making, learning, planning, reasoning, searching, acting, and problem solving. AI is the art of creating computer programs or machines that perform functions that require intelligence when performed by people. AI is concerned with the automation of the intelligent behavior based on the use of computational models. 2 Goals of AI Produced by human art or effort, rather than Artificial: originating naturally. Is the ability to acquire knowledge and use it" Intelligence: [Pigford and Baur]. To make computers more useful by letting them take over dangerous or tedious tasks from Goals of AI: human. Understand principles of human intelligence. 3 Organization of AI Definitions into Four Categories THOUGHT Systems that think Systems that think like humans rationally Systems that act Systems that act BEHAVIOUR like humans rationally HUMAN RATIONAL 4 What is Artificial Intelligence (AI)? Making computer programs think and act like humans (rationally and intelligently). 5 Systems that think like humans: cognitive modeling Cognitive modelling: Cognitive modeling is the process of creating computer-based simulations or models that imitate how humans think and process information. 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) 6 What about the brain? 7  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’). “Thinking rationally is the study of mental faculties ‫ اﻟﻘدرات اﻟﻌﻘﻠﯾﺔ‬through the use of computational models” (Charniak and McDermott) “Thinking rationally is the study of the computations that make it possible to perceive, reason, and act” (Winston) 8 Turing Test 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. Total Turing Machine Includes two more issues: Computer vision: To perceive objects (seeing). Robotics: To move objects (acting) 9 Cognitive Tasks 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. 10 Artificial Intelligence (AI) Activities/ Tasks/ Goals Artificial Intelligence Activities/ Tasks / Goals include: 1. Searching. 2. Planning (using logic). 3. Knowledge representation (using logic). 4. Reasoning (using logic). 5. Prediction. 6. Learning. 7. Decision making (using logic). 8. Problem solving (using logic). 9. Perception (using logic). 10. Simulation. 11 Artificial Intelligence (AI) Areas/ Applications 1. Machine learning. 2. Deep learning. 3. Natural language processing (NLP) (e.g. sentiment analysis, machine translation). 4. Computer vision (e.g. face recognition). 5. Image processing. 6. Internet of things. 7. Robotics. 8. Cyber security. 9. Virtual reality. 10. Social media. 12  11. Agriculture. 12. Business, marketing , and finance. 13. industry/ manufacturing. 14. Sports (e.g. VAR). Artificial 15. Health care and medicine (e.g. medical Intelligence diagnosis). 16. Transportations and automobile (e.g. (AI) Areas/ autonomous vehicles control: drones and self driving cars). Applications 17. Experts systems. 18. Email spam filtering. 19. Climate - Weather forecasting. 20. Entertainment. 13  21. Engineering. 22. Software engineering. 23. Recommendation systems. 24. Game playing (e.g. chess). 25. Bioinformatics (e.g. Gene expression data Artificial analysis). 26. Politics and intelligence (e.g. military logistics). Intelligence 27. Music composition. (AI) Areas/ 28. Web search engines (e.g. Google search). 29. Education. Applications 30. Government. Surveillance. 33. E-commerce. 34. Technology and smart devices. 35. Travel and logistics. 14 Natural Language Processing Applications CHATBOTS. SENTIMENT MACHINE INFORMATION QUESTIONING SPEECH ANALYSIS. TRANSLATION. RETRIEVAL. ANSWERING. RECOGNITION. EMAIL FILTERING. 15 Some of the Main Activities and Areas of AI and Their Inter- dependencies 16 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. I don't care whether a system: Replicates human thought processes. Makes the same decisions as humans. Uses purely logical reasoning. 17  Rational Agents — An agent is an entity that perceives and acts. — Abstractly, an agent is a function from percept histories to actions: [f: P* à 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: à design best program for given machine resources 18 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. 19 Knowledge Representation & Reasoning The second most important concept in AI is Knowledge Representation and reasoning. 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 ? 20  1. More powerful and more useful computers. Some 2. New and improved interfaces. Advantages 3. Solving new problems. of Artificial 4. Better handling of information. Intelligence 5. Relieves information overload. 6. Conversion of information into knowledge. 21  1. Increased costs. The 2. Difficulty with software development - slow and expensive. Disadvantages of Artificial 3. Few experienced programmers. Intelligence 4. Few practical products have reached the market as yet. 22 Machine learning Machine learning (ML) is a subfield of artificial intelligence (AI). It is concerned with computer programs that automatically improve their performance through experience and by the use of data. 23 Life Cycle of Machine Learning Testing dataset Classification Predictions Input data Machine Output training Learning (training model dataset) Clustering Association Learning 24 Types of learning using Machine Learning 1. Supervised learning (machine learning learns from labelled data). 2. Unsupervised learning (machine learning learns from unlabeled data). 3. Semi supervised learning (machine learning learns from labeled and unlabeled data). 4. Reinforcement learning (allows the machine or software agent to learn its behavior based on feedback from the environment (e.g. robotics)). 25  1. Regression (Prediction) ‫اﻟﺗﻧﺑؤ‬ Machine 2. Classification ‫اﻟﺗﺻﻧﯾف‬ Learning 3. Clustering ‫اﻟﺗﺟﻣﯾﻊ‬ Tasks 4. Association ‫اﻟرﺑط‬ 5. Learning ‫اﻟﺗﻌﻠم‬ 26