APPLIED MACHINE LEARNING Applied Machine Learning Introduction 1
APPLIED MACHINE LEARNING Practicalities Contact Information of the Instructors
APPLIED MACHINE LEARNING Practicalities Slides and exercises will be posted on the website of the class the day before class: http://lasa.epfl.ch/teaching/lectures/ML_Msc/index.php http://lasa.epfl.ch/ Teaching Lectures Applied Machine Learning Solutions to the exercises will be posted a week after the exercise session.
APPLIED MACHINE LEARNING Class Format • Lectures: 9h15-11h00 • Exercises (In class): 11h15-12h00 • Lectures alternates with practice sessions held in INN 218, see class schedule. • Attendance to the practice sessions is compulsory. • Attendance to exercise sessions is highly recommended…. 5
APPLIED MACHINE LEARNING TP / Practicals: Group formation https://epfl.doodle.com/poll/ggwdf99a3nwk3ad8 (the link will be sent to you by email) The first practical starts on week 3! 6
APPLIED MACHINE LEARNING Class Syllabus 7
APPLIED MACHINE LEARNING Grading Scheme Practicals (25% of the grade) Performed in team of 2 or 3 people 2 reports – due October 16 and November 20 1 oral presentation – December 11 Written Exam (75% of the grade) 3 hours long Closed book Allowed 1 A4 pages with handwritten notes 8
APPLIED MACHINE LEARNING Pre-requisites Linear Algebra Probability / Statistics Vector / Matrix notation Probability Distribution Function Eigenvalue decomposition Covariance, Expectation Linear dependency Joint, conditional probability Correlation / Statistical Independence Optimization Global versus local optima Brief recap of main algorithms in class Gradient descent Method of Lagrange Multipliers 9
APPLIED MACHINE LEARNING Class Objectives - To understand the basics of some key algorithms of Machine Learning - To apply some of these algorithms with real data and, by so doing, to understand the limitations of the algorithm for real- time systems - To raise in you enough interest for the field, so that you will later try to learn more about it (advanced class at the doctoral school, search on-line, …) - To have more engineers apply these techniques for robust control, signal processing, prediction, learning, etc. 10
APPLIED MACHINE LEARNING Learning Outcomes Main learning outcomes: By the end of the course, the student must be able to: • Choose an appropriate ML method • Assess / Evaluate an appropriate ML method • Apply an appropriate ML method Transversal skills • Write a scientific or technical report. • Make an oral presentation. 11
APPLIED MACHINE LEARNING Today’s class format • Taxonomy and basic concepts in ML • Examples of ML applications • Introduction to best practice in ML 12
APPLIED MACHINE LEARNING What is Machine Learning? Machine Learning encompasses a large set of algorithms that aim at inferring information from what is hidden. This process is often referred to as Data Mining . 13
APPLIED MACHINE LEARNING What is Machine Learning? Machine Learning encompasses a large set of algorithms that aim at inferring information from what is hidden. Independent Component Analysis (ICA) can decompose mixture of signals A. M. Bronstein, M. M. Bronstein, M. Zibulevsky, "On separation of semitransparent dynamic images from static background", Proc. Intl. Conf. on Independent Component Analysis 14 and Blind Signal Separation , pp. 934-940, 2006.
APPLIED MACHINE LEARNING What is Machine Learning? The strength of ML algorithms is that they can apply to arbitrary data. They can recognize patterns from various sources of data. Recognizing human speech. Here this is the wave produced when uttering the word “allright”. Modeling time series : Hidden Markov Models be used to recognize complex sounds, including human speech. 15
APPLIED MACHINE LEARNING What is Machine Learning? Same note played by an oboe Piano note (C5 – do) (hautbois) Classification: Two patterns that are different should still be grouped in the same class 16
APPLIED MACHINE LEARNING What is Machine Learning? ML algorithms are often used to find the representation in which patterns that originally looked different, become similar. 3 sample of 2-dimensional trajectories Same trajectories of a robot’s hand along time. displayed in space(without time). 17
APPLIED MACHINE LEARNING What is Machine Learning? ML algorithms are often used to find the representation in which patterns that originally looked different, become similar. Principal Component Analysis can discover this projection First algorithm we will see in class 3 sample of 2-dimensional trajectories Same trajectories of a robot’s hand along time. displayed in space(without time). 18
APPLIED MACHINE LEARNING What is Machine Learning? Helps compute automatically information that would take days to do by hand. The mapping can be done through support vector regression An algorithm we will see in class Noris, B., Nadel, J, Barker, M., Hadjikhani, N. and Billard, A. (2012) Investigating gaze of children with ASD in naturalistic settings . PLOS ONE. 19
APPLIED MACHINE LEARNING Machine Learning, History • 1940 – The Perceptron (Pitts & MacCulloch) !! • 1960 – The Perceptron (Minsky & Papert) !! • 1960 – “Bellman Curse of Dimensionality” • 1980 – Bounds on statistical estimators (C. Stone) • 1990 – Beginning of high dimensional data (Hundreds variables) • 2000 – High dimensional data (Thousands variables) 20
APPLIED MACHINE LEARNING Machine Learning, History The history traces back to the very first step in Artificial Intelligence (AI). Machine Learning is a new way of thinking in AI that builds strongly on statistics: - probabilistic approach to modeling decision function - modeling of uncertainty in input, output and in the parameters of the model! - data-driven approach as opposed to “knowledge- driven” 21
APPLIED MACHINE LEARNING Machine Learning, History 1980 – The First Machine Learning Workshop was held at Carnegie-Mellon University in Pittsburgh. 1980 – Three consecutive issues of the International Journal of Policy Analysis and Information Systems were specially devoted to machine learning. 1981 - Hinton, Jordan, Sejnowski, Rumelhart, McLeland at UCSD Back Propagation alg. PDP Book 1986 – The establishment of the Machine Learning journal. 1987 – The beginning of annual international conferences on machine learning (ICML). Snowbird ML conference 1988 – The beginning of regular workshops on computational learning theory (COLT). 1990’s – Explosive growth in the field of data mining, which involves the application of machine learning techniques. 22
APPLIED MACHINE LEARNING Why and when do we need learning in Robotics? 23
APPLIED MACHINE LEARNING A typical problem of Robotics Peg and Hole Problem 24
APPLIED MACHINE LEARNING A typical problem of Robotics Peg and Hole Problem 25
APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment 26
APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment B: Engineer the body 27
APPLIED MACHINE LEARNING A typical problem of Robotics A: Engineer the environment B: Engineer the body C: Engineer the controller Systematic search Adaptive control Learning Machine! 28
APPLIED MACHINE LEARNING Machine Learning: definitions Machine Learning is the field of scientific study that concentrates on induction algorithms and on other algorithms that can be said to ``learn.'' Machine Learning Journal, Kluwer Academic Machine Learning is an area of artificial intelligence involving developing techniques to allow computers to “learn”. More specifically, machine learning is a method for creating computer programs by the analysis of data sets, rather than the intuition of engineers. Machine learning overlaps heavily with statistics, since both fields study the analysis of data. Webster Dictionary Machine learning is a branch of statistics and computer science, which studies algorithms and architectures that learn from data sets. WordIQ 29
APPLIED MACHINE LEARNING To engineer the environment is not always desirable Rather, it is desirable to have a system that is Adaptable to different environments That can generalize across tasks Kronander, Burdet and Billard, Learning PegI n Hole Insertionf rom Human Demonstrations, 2013 30
APPLIED MACHINE LEARNING Machines that learn To engineer the environment is not always desirable Rather, it is desirable to have a system that is adaptable to different environments can generalize across tasks 31
APPLIED MACHINE LEARNING Problem I ROWS 1-3 ROWS 4-6 Design an autonomous robot that Make an autonomous robot car distributes graded assignments that can drive people from to a class of students Lausanne to Geneva A: Engineer the environment B: Engineer the body C: Engineer the controller 34
APPLIED MACHINE LEARNING Key features for a good learning system Generalization versus memorization An important feature of a learning system that differentiates it from a pure “memory” is its ability to generalize. 35
Recommend
More recommend
