Computational Methods for Data Analysis

1. Computational Methods for Data Analysis Massimo Poesio INTRO TO MACHINE LEARNING

2. WHAT IS LEARNING • Memorizing something • Learning facts through observation and exploration • Developing motor and/or cognitive skills through practice • Organizing new knowledge into general, effective representations

3. MACHINE LEARNING • Machine Learning • Grew out of work in AI • Solve problems where rules can’t be written by hand

5. SPAM

6. MACHINE LEARNING • Machine Learning • Grew out of work in AI • Solve problems where rules can’t be written by hand • Examples: • Database mining • Large datasets from growth of automation/web. • E.g., Web click data, medical records, biology, engineering • Applications can’t program by hand. • E.g., Autonomous helicopter, handwriting recognition, most of Natural Language Processing (NLP), Computer Vision.

7. Machine Learning • Grew out of work in AI • New capability for computers • Examples: • Database mining • Large datasets from growth of automation/web. • E.g., Web click data, medical records, biology, engineering • Applications can’t program by hand. • E.g., Autonomous helicopter, handwriting recognition, most of Natural Language Processing (NLP), Computer Vision. • Self-customizing programs • E.g., Amazon, Netflix product recommendations • Understanding human learning (brain, real AI).

8. Machine Learning definition • Arthur Samuel (1959). Machine Learning: Field of study that gives computers the ability to learn without being explicitly programmed. • Tom Mitchell (1998) Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

9. “A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.” Suppose your email program watches which emails you do or do not mark as spam, and based on that learns how to better filter spam. What is the task T in this setting? Classifying emails as spam or not spam. Watching you label emails as spam or not spam. The number (or fraction) of emails correctly classified as spam/not spam. None of the above—this is not a machine learning problem.

10. A SPATIAL VIEW LEARNING • Learning to discriminate between spam and non-spam can be pictured as learning how to discriminate between different types of objects in a space

11. A SPATIAL VIEW OF LEARNING The task of the learner is to learn a function that divides the space of examples into black and red

12. EXAMPLE: SPAM SPAM NON-SPAM

13. A MORE DIFFICULT EXAMPLE

14. ONE SOLUTION

15. ANOTHER SOLUTION

16. LEARNING A FUNCTION • Given a set of input / output pairs, find a function that does a good job of expressing the relationship: • Wordsense disambiguation as a function from words (the input) to their senses (the outputs) • Categorizing email messages as a function from emails to their category (spam, useful) • A checker playing strategy a function from moves to their values (winning, losing)

17. WAYS OF LEARNING A FUNCTION • SUPERVISED: given a set of example input / output pairs, find a rule that does a good job of predicting the output associated with an input • UNSUPERVISED learning or CLUSTERING: given a set of examples, but no labelling, group the examples into “natural” clusters • REINFORCEMENT LEARNING: an agent interacting with the world makes observations, takes action, and is rewarded or punished; the agent learns to take action in order to maximize reward

18. Supervised Learning

19. EXAMPLE: HOUSING PRICE PREDICTION Price ($) in 1000’s Size in feet2 Supervised Learning “right answers” given Regression: Predict continuous valued output (price)

20. Spam, non-spam Classification Discrete valued output (0 or 1) 1(Y) Spam? 0(N) Length of message (words) Length of message (words)

21. Occurrence of word ‘Nigeria’ • Occurrence of word ‘million dollars’ • … From: Length of message

22. You’re running a company, and you want to develop learning algorithms to address each of two problems. Problem 1: You have a large inventory of identical items. You want to predict how many of these items will sell over the next 3 months. Problem 2: You’d like software to examine individual customer accounts, and for each account decide if it has been hacked/compromised. Should you treat these as classification or as regression problems? Treat both as classification problems. Treat problem 1 as a classification problem, problem 2 as a regression problem. Treat problem 1 as a regression problem, problem 2 as a classification problem. Treat both as regression problems.

23. Unsupervised Learning

24. Supervised Learning x2 x1

25. Unsupervised Learning x2 x1

26. Unsupervised Learning x2 x1

29. Genes Individuals [Source: Daphne Koller]

30. Image credit: NASA/JPL-Caltech/E. Churchwell (Univ. of Wisconsin, Madison) Social network analysis Organize computing clusters Market segmentation Astronomical data analysis

31. Of the following examples, which would you address using an unsupervised learning algorithm? (Check all that apply.) Given email labeled as spam/not spam, learn a spam filter. Given a set of news articles found on the web, group them into set of articles about the same story. Given a database of customer data, automatically discover market segments and group customers into different market segments. Given a dataset of patients diagnosed as either having diabetes or not, learn to classify new patients as having diabetes or not.

32. History of Machine Learning • 1950s • Samuel’s checker player • Selfridge’s Pandemonium • 1960s: • Neural networks: Perceptron • Pattern recognition • Learning in the limit theory • Minsky and Papert prove limitations of Perceptron • 1970s: • Symbolic concept induction • Winston’s arch learner • Expert systems and the knowledge acquisition bottleneck • Quinlan’s ID3 • Michalski’s AQ and soybean diagnosis • Scientific discovery with BACON • Mathematical discovery with AM

33. History of Machine Learning (cont.) • 1980s: • Advanced decision tree and rule learning • Explanation-based Learning (EBL) • Learning and planning and problem solving • Utility problem • Analogy • Cognitive architectures • Resurgence of neural networks (connectionism, backpropagation) • Valiant’s PAC Learning Theory • Focus on experimental methodology • 1990s • Data mining • Adaptive software agents and web applications • Text learning • Reinforcement learning (RL) • Inductive Logic Programming (ILP) • Ensembles: Bagging, Boosting, and Stacking • Bayes Net learning

34. History of Machine Learning (cont.) • 2000s • Support vector machines • Kernel methods • Graphical models • Statistical relational learning • Transfer learning • Sequence labeling • Collective classification and structured outputs • Computer Systems Applications • Compilers • Debugging • Graphics • Security (intrusion, virus, and worm detection) • E mail management • Personalized assistants that learn • Learning in robotics and vision

35. READINGS • English: • T. Mitchell, Machine Learning, Mc-Graw Hill, ch.1 • Italian: • R. Basili & A. Moschitti, Apprendimentoautomatico, in F. Bianchini et al, Instrumentumvocale

36. THANKS • I used materials from • Andrew Ng’s Coursera course at Stanford • Ray Mooney’s ML course at Utexas