ADAPTIVE SYSTEMS & USER MODELING Alexandra I. Cristea USI intensive course Adaptive Systems April-May 2003.

• Slide 1

ADAPTIVE SYSTEMS & USER MODELING Alexandra I. Cristea USI intensive course Adaptive Systems April-May 2003 Slide 2 Introduction Course site: http://wwwis.win.tue.nl/~alex/HTML/USI/index.html http://wwwis.win.tue.nl/~alex/HTML/USI/index.html Course schedule, principles, tasks, etc. Slide 3 Module division I. Adaptive Systems and User Modeling course II. Project work Slide 4 Adaptive System course parts 1.Adaptive Systems, Generalities 2.User Modeling 3.Data representation for AS 4.Adaptive Systems, invited talk: Genetic Algorithms Slide 5 Project work parts 1.Presentation MOT 2.Presentation project assignments 3.Group work 4.Project and results presentation and evaluation Slide 6 Part 1: Adaptive Systems Slide 7 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 8 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 9 Foundations of Adaptive Computation: Natural Adaptive Systems Slide 10 What are Adaptive Systems in Nature? Examples? Slide 11 Natural Systems How do adaptive systems in nature compute? (De-)centralized/collective computation Computation over spatial extent Probabilistic computation Computation in continuous-state systems Computation in neural systems Slide 12 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 13 Artificial Adaptive Systems Slide 14 Slide 15 Types of Artificial Adaptive Systems Adaptive Hypermedia, Agents, Game of Life, Ant Algorithms, Genetic Algorithms, Artificial Life, Genetic Art, Brain Building, Genetic Programming, Cellular Automata, Cellular Computing, Cellular Neural Networks, Cellular Programming, Complex Adaptive Systems, Quantum Computing, Cybernetics, Reversible Computing, DNA Computing, Self-Replication, Evolutionary Computation, Evolvable Hardware, Virtual Creatures, Flocking Behaviour, etc. Slide 16 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 17 Artificial Adaptive Systems Examples Slide 18 Example1 Evolving artificial creatures, Karl Sims: http://biota.org/ksims/blockies/index.html#video Slide 19 Example2 Ants Slide 20 TSP pb. Slide 21 Ex.3: NN: spatial forms Slide 22 Ex. 4: NN:OCR Slide 23 Ex.5: intelligent agent Steve http://www.isi.edu/isd/VET/steve-demo.html Slide 24 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 25 General Classification of AS Software Hardware Combined Slide 26 Example: combined Khepera robot Slide 27 ElementsTechnical Information Processor Motorola 68331, 25MHz [improved] RAM512 Kbytes [improved] Flash512 Kbytes Programmable via serial port [new] Motion2 DC brushed servo motors with incremental encoders SpeedMax: 60 cm/s, Min: 2 cm/s Sensors 8 Infra-red proximity and ambient light sensors with up to 100mm range I/O3 Analog Inputs (0-4.3V, 8bit) PowerPower Adapter Rechargeable NiMH Batteries[improved] Autonomy 1 hour, moving continuously [improved]. Communica tion Standard Serial Port, up to 115kbps [improved] Extension Expansion modules can be added to the robot SizeDiameter: 70 mm Height: 30 mm WeightApprox 80 g Slide 28 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 29 Applications of Artificial Adaptive Systems Slide 30 Applications of Adaptive Systems expert systems (e.g. medical diagnosis) data mining (e.g. search engines) computational linguistics games Slide 31 More Applications of Adaptive Computation Parallel computing: evolution of cellular automata Molecular biology: molecular evolution, design of useful molecules, protein design Computer security: immune systems for computers Intelligent agents and robotics Scientific modeling: evolution, ecologies, economies, insect societies, immune systems, organizations Slide 32 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 33 What can we adapt to? What kind of information can we use to adapt, in general? From whom/ what do we get this information? What means adaptation in this context? Slide 34 What can we adapt to? What kind of information can we use to adapt, in general? External: Static Variables values: Light intensity, Dynamics: Changes, Other participants behavior Internal: Needs: hunger Prediction: (anticipation) Slide 35 What can we adapt to? From whom/ what do we get this information? Other participants Existing variables Slide 36 What can we adapt to? What means adaptation in this context? The adaptive system reacts to the environment (static, dynamics) and to itself towards some benefit Slide 37 Overview: AS 1.Adaptive Systems: Foundations 2.Artificial Adaptive Systems 3.Examples 4.General Classification 5.Applications 6.What can we adapt to? 7.Ultimate goal artificial AS? 8.Conclusion Slide 38 A Comparison between Adaptive and Adaptable Systems Gerhard Fischer 1 HFA Lecture, OZCHI2000 Slide 39 Ultimate Goal of Artificial Adaptive Systems? Intelligence Slide 40 Conclusions Man is trying to imitate nature with artificial AS Why? Because man-made machines with predefined behavior cannot cover all aspects Note: Adaptation < Learning < Intelligence Slide 41 Conclusions 2 Adaptation in general doesnt mean to a human [] However, adaptation to a human is more challenging!