* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download To append for course “Soft computing”
Survey
Document related concepts
Philosophy of artificial intelligence wikipedia , lookup
Ecological interface design wikipedia , lookup
Collaborative information seeking wikipedia , lookup
Wizard of Oz experiment wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Self-reconfiguring modular robot wikipedia , lookup
Personal knowledge base wikipedia , lookup
Incomplete Nature wikipedia , lookup
History of artificial intelligence wikipedia , lookup
Transcript
COURSE “Intelligent Systems” 2005 Fall Lecturer - Professor, Dr. Andrey V.Gavrilov. To append for course “Intelligent systems” Course Description This course will provide students the basic concepts of different methods and tools of knowledge engineering for building of intelligent systems based on knowledge, such as, logic, rules, frames, semantic nets. The course will provide students the knowledge about applied intelligent systems. In particular, expert systems, intelligent systems, systems based on natural language processing. This course contains methodology and technology of development of expert systems, technologies for building of systems understanding of natural language. For all other students: Grading Policy (tentative) Midterm 50% Final Total 50% 100% Lecturer - Professor, Dr. Andrey V.Gavrilov. Course includes 16 lectures and 8 practical works. Contents of lectures: 1. Introduction in AI History of AI Role of AI in informatics and Civilization Two approaches to development of AI – Neuroinformatics and Logical AI 2. Features of Kinds of Applied AI Systems Experts systems Intelligent Robots Natural language Processing 4. Main definitions of Knowledge Engineering 5. Methods of Knowledge Representation and Solving of tasks Space of states and search in it Predicate Logic Fuzzy Sets and Fuzzy Logic Pseudo-Physics logics Rules Semantic Nets Frames Soft Computing 6. Comparison and Selection of different Methods of Knowledge Representation 7. Languages and tools for Knowledge Engineering Introduction to programming in PROLOG Features of LISP KR-languages 8. Expert Systems Conditions for efficient use of Expert Systems Steps of development of Expert System Features of architectures of Expert Systems 9. Machine learning Induction Neural networks Reinforcement learning Genetic algorithms 10. Hybrid Intelligent Systems Combination of knowledge representation methods, Review of Hybrid Expert Systems (HES), Classification of HES, Architecture of ESWin (toolkit for building of HES) 11. Paradigm of Distributed (multi-agent) Intelligent Systems 12. Paradigm of Ontology and Semantic WEB 13. Intelligent Robots Classification of robots and its control systems Functions of control systems of Robots Task solving by mobile robots Features of Development of Humanoid Robots 14. Natural language processing Problems Kinds of NLP-systems Review of methods of NLP, Review of use of neural networks in NLP systems, Architecture of learning software for search of documents by query on Natural Language Introduction to speech recognition 15. Conclusions. The future of Artificial Intelligence and Applied AI Systems, Practical works are based on original products, developed by author and his colleagues: - ESWin, software for building of hybrid expert systems, - Software Alang+Finder for search of documents by query on Natural Language, - Software AnalDB for Data Base Analyzing by Neural Networks (perceptron + Hopfield model). More information on this software is available from http://www.insycom.ru and http://ermak.cs.nstu.ru/islab/ Date 13.09. Kind Lecture 1 15.09 Lecture 2 Title Introduction in AI. What is AI? History of AI. Role of AI in informatics and Civilization. Two approaches to development of AI – Neuroinformatics and Logical AI. Applied AI Systems. Kinds. Experts systems, Intelligent Robots. Room 445 445 20.09 22.09 27.09 29.09 5.10 7.10 11.10 13.10 17.10 19.10 25.10 27.10 1.11 3.11 8.11 10.11 15.11 17.11 22.11 24.11 29.11 1.12 6.12 8.12 13.12 15.12 20.12 22.12 Lecture 3 Main definitions of Knowledge Engineering. Kinds of knowledge representations. Intelligent agents. Logic for Knowledge representation. 1order logic. Lecture 4 Solving of tasks in 1-order logic. Introduction to logic programming. Lecture 5 Programming in Prolog. Lecture 6 Semantic nets and frames. Comparison of Knowledge representations and problem of selection of its. Kinds of combinations of different methods of KR. Lecture 7 Methods of solving of tasks in knowledge-based learning. Searching in state-space, logic inference, matching, using of context, in particular, inheritance. Lecture 8 Problem of acquisition of knowledge. Kinds of methods. Induction. Colloquium 1 Positive and negative of logic in thinking and AI. Lecture 9 Tools of knowledge engineering. Kinds. Examples. Lecture 10 Introduction to programming in Lisp Lecture 11 Architecture of Expert Systems. Characteristics of Expert Systems. Steps of development of ES. Lecture 12 Tools for development of ES. Example of expert shell – ESWin Lecture 13 Review of modern Expert Systems Exam MIDTERM EXAM Lecture 14 Intelligent robots. Classification of modern robots. Functions of control system. Features of development of humanoid robots. Lecture 15 Review of intelligent robots. Lecture 16 Example of shell for simulation of mobile robot Webots. Introduction to standart of mobile robots – JAUS. Lecture 17 Control systems of robots based on NN. Lecture 18 Problems of natural language processing (NLP). Lecture 19 Methods of simulation of understanding of NL. Lecture 20 Examples of NLP in searching systems. Lecture 21 Example of ALICE-like dialog system. Language AIML for ALICE-like systems Colloquium 2 Test of Turing and problem of testing of Intelligence. Lecture 22 Introduction to recognition of speech. Lecture 23 Introduction to Intelligent Data Analyzing (IDA). Example of system for Data Analyzing based on neural networks. Lecture 24 Ontologies. Semantic WEB. Lecture 25 Multi-agent systems. Colloquium 3 Future of AI. Dangers and problems of development of AI. Lecture 26 FINAL EXAM 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 445 Suggested reading: 1. Arbib, M. A. The Metaphorical Brain. New York: Wiley (1990). 2. Bradshaw, J. (Ed.) Software Agents. Cambridge, MA: MIT Press (1997). 3. Honavar, V. & Uhr, L. (Ed.) Artificial Intelligence and Neural Networks: Steps Toward Principled Integration. San Diego, CA: Academic Press (1994). 4. Jackson P. Introduction to Expert Systems. Addison Wesley, Publishing Company, Inc. (1998). 5. Jones M.T. AI application Programming. Charles River Media, Inc., Hingham, Massachusetts (2003). 6. Luger G.F. Artificial Intelligence. Structures and Strategies for Complex Problem Solving. Addison Wesley (2002). (Electronic content of separate parts is available). 7. Minsky, M. Society of Mind. New York: Basic Books (1986). 8. Mitchell T. Machine Learning. MacGraw Hill (1997). 9. Nilsson, N., The Mathematical Foundations of Learning Machines, San Francisco: Morgan Kaufmann (1990). 10. Nilsson, N., Principles of Artificial Intelligence, San Francisco: Morgan Kaufmann (1980). 11. Newell, A. Unified Theories of Cognition. Cambrdge, MA: Harvard University Press (1990). 12. Russel, S. & Norvig, P., Artificial Intelligence - a modern approach. Englewood Cliffs, NJ: Prentice Hall (2002). (Electronic content of separate parts is available). 13. Sowa J. Knowledge Representation: Logical, Philosophical and Computational Foundation. Pacific Grove, CA: Brooks/Cole (2000). 14. Sutton R.S., Barto A.J. Reinforcement Learning: An Introduction. The MIT Press Cambridge, Massachusetts, London. (Electronic book is available). 15. Wasserman, P. Advanced Methods in Neural Computing. New York: Van Nostrand Rheinhold (1993).