learning in intelligent systems
play

Learning in Intelligent Systems October 14, 2016 Janyl Jumadinova - PowerPoint PPT Presentation

Learning in Intelligent Systems October 14, 2016 Janyl Jumadinova Overview of Learning 2/19 Learning in Humans The act / process of acquiring, modify or reinforcing knowledge or skills through synthesizing different types of new or existed


  1. Learning in Intelligent Systems October 14, 2016 Janyl Jumadinova

  2. Overview of Learning 2/19

  3. Learning in Humans ◮ The act / process of acquiring, modify or reinforcing knowledge or skills through synthesizing different types of new or existed information. 3/19

  4. Learning in Humans ◮ The act / process of acquiring, modify or reinforcing knowledge or skills through synthesizing different types of new or existed information. ◮ Key to human survival. 3/19

  5. Learning in Humans ◮ The act / process of acquiring, modify or reinforcing knowledge or skills through synthesizing different types of new or existed information. ◮ Key to human survival. ◮ Progress over time tends to follow learning curves (relatively permanent). 3/19

  6. Learning in Computing Systems ◮ Computational methods using “experience” to improve performance. 4/19

  7. Learning in Computing Systems ◮ Computational methods using “experience” to improve performance. ◮ Experience − data driven task 4/19

  8. Learning in Computing Systems ◮ Computational methods using “experience” to improve performance. ◮ Experience − data driven task ◮ Computer science – involves learning algorithms, analysis of complexity, and theoretical guarantees. 4/19

  9. Learning in Computing Systems Artificial intelligence | Machine learning 5/19

  10. Learning in Computing Systems Artificial intelligence | Machine learning ◮ Computer program(s) with adaptive mechanisms that enable computer / machine to learn from experience /example / analogy / rewards. 5/19

  11. Learning in Computing Systems Artificial intelligence | Machine learning ◮ Computer program(s) with adaptive mechanisms that enable computer / machine to learn from experience /example / analogy / rewards. ◮ It improves the performance of an intelligent system over time (e.g, reducing error rate, improving rewards). 5/19

  12. Why Learning in Computing Systems? ◮ Understand and improve efficiency of human learning / understanding. 6/19

  13. Why Learning in Computing Systems? ◮ Understand and improve efficiency of human learning / understanding. ◮ Discover new things or structure that is unknown to humans. 6/19

  14. Why Learning in Computing Systems? ◮ Understand and improve efficiency of human learning / understanding. ◮ Discover new things or structure that is unknown to humans. ◮ Fill in skeletal or incomplete knowledge / expert specifications about a domain. 6/19

  15. Applications of Learning Mainly in decision making / pattern recognition / intelligent systems. 7/19

  16. Applications of Learning Mainly in decision making / pattern recognition / intelligent systems. ◮ Robot navigation. ◮ Automatic speech recognition (Siri in iPhone, Google speech-to-text search). ◮ Search and recommendation (Google, Amazon, eBay). ◮ Financial prediction, fraud detection, medical diagnosis. ◮ Video games, data visualization. 7/19

  17. Black-box Learning 8/19

  18. Learning Architecture 9/19

  19. Learning Paradigms ◮ Supervised learning - input-output relationships 10/19

  20. Learning Paradigms ◮ Supervised learning - input-output relationships ◮ Unsupervised learning - relationship among inputs 10/19

  21. Learning Paradigms ◮ Supervised learning - input-output relationships ◮ Unsupervised learning - relationship among inputs ◮ Reinforcement learning - input-action relates to rewards / punishment 10/19

  22. Learning Paradigms ◮ Supervised learning - input-output relationships ◮ Unsupervised learning - relationship among inputs ◮ Reinforcement learning - input-action relates to rewards / punishment ◮ Rule learning - discovering common relationship to develop rules 10/19

  23. Supervised Learning Given examples of inputs and corresponding desired outputs. 11/19

  24. Supervised Learning Given examples of inputs and corresponding desired outputs. Tasks : ◮ Classification (categorizing output: correct class) ◮ Regression (continuous output to predict output based for new inputs) ◮ Prediction (classify / regression on new input sequences) 11/19

  25. Supervised Learning 12/19

  26. Unsupervised Learning Given only inputs and automatically discover representations, features, structure etc. 13/19

  27. Unsupervised Learning Given only inputs and automatically discover representations, features, structure etc. Tasks : ◮ Clustering (to group similar data into a finite number of clusters / groups) ◮ Vector Quantization (compress / decode dataset into a new representation but maintaining internal information) ◮ Outlier Detection (select highly unusual cases) sequences) 13/19

  28. Unsupervised Learning 14/19

  29. Reinforcement Learning ◮ Learning approach of getting a computer system to act in the world so as to maximize its rewards. 15/19

  30. Reinforcement Learning ◮ Learning approach of getting a computer system to act in the world so as to maximize its rewards. ◮ Consider teaching a domestic animal. We cannot tell it what to do, but we can reward / punish if it does the right/ wrong thing. 15/19

  31. Reinforcement Learning ◮ Learning approach of getting a computer system to act in the world so as to maximize its rewards. ◮ Consider teaching a domestic animal. We cannot tell it what to do, but we can reward / punish if it does the right/ wrong thing. ◮ Process to determine what it did that made it get the reward / punishment – “credit assignment problem.” 15/19

  32. Reinforcement Learning 16/19

  33. Rule Learning Given multiple measurements to discover very common settings in term of causal-effect. 17/19

  34. Rule Learning Given multiple measurements to discover very common settings in term of causal-effect. Tasks : ◮ Association rules (to group similar data into a finite number of clusters / groups) 17/19

  35. Rule Learning Given multiple measurements to discover very common settings in term of causal-effect. Tasks : ◮ Association rules (to group similar data into a finite number of clusters / groups) ◮ Classification rules (compress / decode dataset into a new representation but maintaining internal information) 17/19

  36. Rule Learning 18/19

  37. Learning Paradigms and Some Techniques 19/19

Recommend


More recommend