* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Lecture 1 Characterisations of AI
Artificial intelligence in video games wikipedia , lookup
Human–computer interaction wikipedia , lookup
Concept learning wikipedia , lookup
Computer vision wikipedia , lookup
Visual Turing Test wikipedia , lookup
Technological singularity wikipedia , lookup
Ecological interface design wikipedia , lookup
Pattern recognition wikipedia , lookup
Logic programming wikipedia , lookup
Genetic algorithm wikipedia , lookup
Knowledge representation and reasoning wikipedia , lookup
Machine learning wikipedia , lookup
Human-Computer Interaction Institute wikipedia , lookup
Embodied cognitive science wikipedia , lookup
Computer Go wikipedia , lookup
Intelligence explosion wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Ethics of artificial intelligence wikipedia , lookup
Artificial Intelligence 1. Characterisations of AI Course 254482 Lecturer : Sukchatri PRASOMSUK University of Phayao, ICT Slide by © Simon Colton Department of Computing, Imperial College, London 1 Overview of Characterisations 1.1 Long term goals – 1.2 Inspirations – Hack away or theorise 1.4 General tasks to achieve – 2 How do we get machines to act intelligently? 1.3 Methodology employed – What do we want to achieve with AI? Reason, learn, discover, compete, communicate, … 1.5 - 1.8 Fine grained characterisations 1.1 Long Term Goals 1. Produce intelligent behaviour in machines Why use computers at all? – – We do intelligent things – So get computers to do intelligent things Monty Hall problem – 3 They can do things better than us Big calculations quickly and reliably Would a computer program get this wrong? 1.1 Long Term Goals 2. Understand human intelligence in society – Big question: what is intelligence? – Helped to study Rogerian psychotherapy How does society affect intelligence – 4 Smaller questions: language, attention, emotion Example: The ELIZA program – Aid to philosophy, psychology, cognitive science AI used to look into social behaviour 1.1 Long Term Goals 3. Give birth to new life forms Oldest question of all – One approach: model life in silicon – Create “artificial” life forms (ALife) Evolutionary algorithms – – 5 Meaning of life – (if it worked for life on planet earth…) Hope “life” will be an emergent property Can tame this for more utilitarian needs 1.1 Long Term Goals 4. Add to scientific knowledge – – Example: complexity of algorithms – P = NP? Another example: – 6 Often ignored that AI produces big scientific questions Investigate intelligence, life, information What concepts can be learned by certain algorithms (computational learning theory) 1.2 Inspirations for AI (แรงบันดาลใจสาหรับ AI) Major question: – Use what we have available: – – – 7 “How are we going to get a machine to act intelligently to perform complex tasks?” Logic, introspection, brains Evolution, planet earth Society, fast computers 1.2 Inspirations for AI 1. Logic – – Example: automated reasoning – 8 Proving theorems using deduction(พิสูจน์ทฤษฎีบทโดยใช้การหัก) Advantage of logic: – Studied intensively within mathematics Gives a handle on how to reason intelligently We can be very precise (แม่นยา) (formal) about our programs Disadvantage of logic: – Theoretically possible doesn’t mean practically achievable 1.2 Inspirations for AI 2. Introspection (วิปัสสนาหรื อการใคร่ ครวญ) – Heuristics to improve performance – 9 Implement the ways (rules) of the experts Example: MYCIN (blood disease diagnosis) – Rules of thumb derived from perceived human behaviour Expert systems – Humans are intelligent, aren’t they? Performed better than junior doctors Introspection can be dangerous 1.2 Inspirations for AI 3. Brains – Neurologist tell us about: – In hardware and software (mostly software now) Build neural structures – 10 Networks of billions of neurons Build artificial neural networks – Our brains and senses are what give us intelligence Interactions of layers of neural networks 1.2 Inspirations for AI 4. Evolution – So, simulate the evolutionary process (กระบวนการ วิวฒั นาการ) – Simulate genes, mutation, inheritance, fitness, etc. Genetic algorithms and genetic programming – – 11 Our brains evolved through natural selection Used in machine learning (induction) Used in Artificial Life simulation 1.2 Inspirations for AI 5. Evolution on Earth – Moving around and avoiding objects – – 12 More intelligent than playing chess AI should be embedded in robotics – We evolved to survive in a dynamic environment Sensors (vision, etc.), locomotion, planning Hope that intelligent behaviour emerges Behaviour based robotics – Start with insect like behaviour 1.2 Inspirations for AI 6. Society (ด้านสังคม) – – Software should therefore – Cooperate and compete to achieve tasks Multi-agent systems – – 13 Humans interact to achieve tasks requiring intelligence Can draw on group/crowd psychology Split tasks into sub-tasks Autonomous agents interact to achieve their subtask 1.2 Inspirations for AI 7. Computer science – Allows us to write intelligent programs – Rather than reasoning intelligently Example: computer chess – 14 In “bad” ways: using brute force Doing massive searches – Computers and operating systems got very fast – Some people say that this “isn’t AI” Drew McDermott disagrees 1.3 Methodologies “Neat” approach วิธีการที่มีระเบียบ – Ground programs in mathematical rigour (ความเม่นยาทาง คณิ ตศาสตร์) – Use logic and possibly prove things about programs “Scruffy” approach (ยูย่ ,ี่ สกปรก) – Write programs and test empirically (ทางสังเกตุ) – See which methods work computationally “Smart casual”: use both approaches – 15 – See AI as an empirical science and technology Needs theoretical development and testing 1.4 General Tasks AI is often presented as – – Some problems attacked with AI techniques: – – – – – – 16 A set of problem solving techniques Most tasks can be shoe-horned into a “problem” spec. Getting a program to reason rationally Getting a program to learn and discover Getting a program to compete Getting a program to communicate Getting a program to exhibit signs of life Getting a robot to move about in the real world 1.5 Generic Techniques Automated Reasoning – Machine Learning – 17 N-grams, parsing, grammar learning Robotics – Neural nets, ILP, decision tree learning Natural language processing – Resolution, proof planning, Davis-Putnam, CSPs Planning, edge detection, cell decomposition Evolutionary approaches – Crossover, mutation, selection 1.6 Representation/Languages AI catchphrase – Some general schemes – – – Predicate logic, higher order logic Frames, production rules Semantic networks, neural nets, Bayesian nets Some AI languages developed – – 18 “representation, representation, representation” Prolog, LISP, ML (Perl, C++, Java, etc. also very much used) 1.7 Application Areas Applications which AI has been used for: – – – – – AI takes as much as it gives to domains – 19 Art, astronomy, bioinformatics, engineering, Finance, fraud detection (การตรวจสอบการทุจริ ต), law, mathematics, Military, music, story writing, telecommunications Transportation, tutoring, video games, web search And many more… – AI is not a slave to other applications It benefits from input from other domains 1.8 Final Products Some AI programs/robots are well developed Example software: – – – Example hardware: – – – 20 Otter (theorem prover, succesor to EQP) Progol (machine learning) Eliza (psychotherapy!!) จิตบาบัด SHAKEY (very old now) Rodney Brooks’ vacuum cleaner Museum tour guide