Presentation Transcript

1. Introduction to Machine LearningBITS C464/BITS F464

   NavneetGoyal Department of Computer Science, BITS-Pilani, Pilani Campus, India
2. Machine Learning Humour Source – http://www.kdnuggets.com/2012/12/machine-learning-data-mining-humor.html
3. Source - http://diegoferrin.wordpress.com
4. Introduction Related Fields Artificial Intelligence Statistics Data Mining
5. Machine Learning Humour What is the difference between statistics, machine learning, AI and data mining? If there are up to 3 variables, it is statistics. If the problem is NP-complete, it is machine learning. If the problem is PSPACE-complete, it is AI. If you don't know what is PSPACE-complete, it is data mining. Source – http://www.kdnuggets.com/2012/12/machine-learning-data-mining-humor.html
6. What is Machine Learning? Machines DO Machines LEARN Shift in paradigm! Machines can be made to learn! How and for what purpose? How? By writing algorithms! Purpose: Mainly to Predict and to take Decisions!
7. Types of Learning Supervised Unsupervised Semi-supervised Reinforcement Active Deep
8. Introduction Zoologists study learning in animals Psychologists study learning in humans In this course, we focus on “Learning in Machines” Course Objective Study of approaches and algorithms that can make a machine learn
9. Introduction Machine Learning Subarea of AI that is concerned with algorithms/programs that can make a machine learn Improve automatically with experience For example- doctors learning from experience Imagine computers learning from medical records and suggesting treatment (automated diagnosis & prescription)
10. Machine Learning A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E.
11. Interesting Problems Speech and Hand Writing Recognition Robotics (training moving robots) Search Engine (context aware) Learning to drive autonomous vehicle Medical Diagnosis Detecting credit card fraud Computational Bioinformatics Game Playing
12. What is Machine Learning? To solve a problem, we need an algorithm! For example: sorting a list of numbers Input: list of numbers Output: sorted list of numbers For some tasks, like filtering spam mails Input: an email Output: Y/N We do not know how to transform Input to Output Definition of Spam changes with time and from one individual to individual What to DO? Reference: E Alpaydin’s Machine Learning Book, 2010 (MIT Press)
13. What is Machine Learning? Collect lots of emails (both genuine and spam) “Learn” what constitutes a spam mail (or for that matter a genuine mail) Learn from DATA!! For many similar problems, we may not have algorithm(s), but we do have example data (called Training Data) Ability to process training data has been made possible by advances in computer technology Reference: E Alpaydin’s Machine Learning Book, 2010 (MIT Press)
14. What is Machine Learning? Face Recognition!!! We humans are so good at it!!! Ever thought how we do it, despite Different light conditions, pose, hair style, make up, glasses, ageing etc.. Since we do not know how we do it, we can not write a program to do it ML is about making inference from a sample Reference: E Alpaydin’s Machine Learning Book, 2010 (MIT Press)
15. Machine Learning Applications What kind of data I would require for learning? Credit card transactions Face Recognition Spam filter Handwriting/Character Recognition
16. Handwriting Recognition Task T recognizing and classifying handwritten words within images Performance measure P percent of words correctly classified Training experience E a database of handwritten words with given classifications
17. Handwriting Recognition
18. Pattern Recognition Example Handwriting Digit Recognition Reference: Christopher M Bishop: Pattern Recognition & Machine Leaning, 2006 Springer
19. Pattern Recognition Example Handwriting Digit Recognition Non-trivial problem due to variability in handwriting What about using handcrafted rules or heuristics for distinguishing the digits based on shapes of strokes? Not such a good idea!! Proliferation of rules Exceptions of rules and so on… Adopt a ML approach!! Reference: Christopher M Bishop: Pattern Recognition & Machine Leaning, 2006 Springer
20. Pattern Recognition Example Handwriting Digit Recognition Each digit represented by a 28x28 pixel image Can be represented by a vector of 784 real no.s Objective: to have an algorithm that will take such a vector as input and identify the digit it is representing Take images of a large no. of digits (N) – training set Use training set to tune the parameters of an adaptive model Each digit in the training set has been identified by a target vector t, which represents the identity of the corresp. digit. Result of running a ML algo. can expressed as a fn. y(x) which takes input a new digit x and outputs a vector y. Vector y is encoded in the same way as t The form of y(x) is determined through the learning (training) phase Reference: Christopher M Bishop: Pattern Recognition & Machine Leaning, 2006 Springer
21. Pattern Recognition Example Generalization The ability to categorize correctly new examples that differ from those in training Generalization is a central goal in pattern recognition Preprocessing Input variables are preprocessed to transform them into some new space of variables where it is hoped that the problem will be easier to solve (see fig.) Images of digits are translated and scaled so that each digit is contained within a box of fixed size. This reduces variability. Preprocessing stage is referred to as feature extraction New test data must be preprocessed using the same steps as training data Reference: Christopher M Bishop: Pattern Recognition & Machine Leaning, 2006 Springer
22. Linear Classifiers in High-Dimensional Spaces Constructed Feature 2 Var1 Var2 Constructed Feature 1 Find function (x) to map to a different space Go back
23. A word about Preprocessing!! Preprocessing Can also speed up computations For eg.: Face detection in a high resolution video stream Find useful features that are fast to compute and yet that also preserve useful discriminatory information enabling faces to be distinguished form non-faces Avg. value of image intensity in a rectangular sub-region can be evaluated extremely efficiently and a set of such features are very effective in fast face detection Such features are smaller in number than the number of pixels, it is referred to as a form of Dimensionality Reduction Care must be taken so that important information is not discarded during pre processing Reference: Christopher M Bishop: Pattern Recognition & Machine Leaning, 2006 Springer