Greg Grudic Machine Learning Greg Grudic Artificial Intelligence 2 Machine Learning CSCI 4202 1 Tuesday and Thursday 02 00pm 03 15pm in ECCR 118 303 492 4419 grudic cs colorado edu http www cs colorado edu grudic teaching CSCI4202 2004 Phone Email Course URL Machine Learning Tuesday and Wednesday 4 30 5 30 Office Hours Greg Grudic ECOT 525 Office Instructor Professor Greg Grudic Location Admin Stuff 1 2 30 30 10 30 Machine Learning Homework Project Class participation Final exam Greg Grudic Course Textbook Artificial Intelligence A Modern Approach by Stuart Russell and Peter Norvig Grading Admin Stuff 2 3 Greg Grudic Machine Learning 4 ML algorithms are at the heart of many modern computer applications Why is machine learning important What does it mean for a machine to learn A fundamental understanding of the basic concepts behind machine learning Goal of the Course Machine Learning Economics medical diagnosis robotics computer vision manufacturing inventory control elevator operation Data doubles every year Dunham 2002 ML algorithms are used to make sense of this data Data mining Which gene is responsible for the cancer that runs in my family Human genome project Bioinformatics Searching the web for things of interest Document characterization Making it easier to interact with a PC by anticipating what I am doing User interfaces Is passenger 57 likely to hijack a plane Profiling Who should a company target for advertising Marketing Greg Grudic Where can ML be found 5 Greg Grudic Machine Learning 6 The automation of activities that we associate with human thinking activities such as decision making problem solving learning Bellman 1978 The study of mental faculties through the use of computational models Charniak and McDermott 1985 The study of how to make computers do things at which at the moment people are better Rich and Knight 1991 The branch of computer science that is concerned with the automation of intelligent behavior Luger and Stubblefield 1993 ML is part of Artificial Intelligence What is AI Clean my house Cook when I don t want to Wash my clothes Cut my grass Fix my car or take it to be fixed i e do the things that I don t feel like doing Greg Grudic Machine Learning Therefore AI is to me the science of building machines agents that act rationally with respect to a goal I want to build a robot that will My Personal View of AI 7 Greg Grudic Machine Learning Aristotle Nicomachean Ethics Every art and every inquiry and similarly every action and pursuit is thought to aim at some good This is not a new idea The right thing that which is expected to maximize goal achievement doing things I don t feel like doing given the available information An agent is an entity that perceives and acts A rational agent is one that does the right thing What is a Rational Agent 8 Greg Grudic Machine Learning Learning Representation Reasoning Elements of AI 9 Greg Grudic Machine Learning Representation Learning My Elements of AI 10 Greg Grudic ML techniques can Machine Learning 11 It is not possible to hand code knowledge about anything but the most trivial problem domains Expert Systems mostly failed because an expert e g doctor doesn t know how to formalize code what makes her an expert For Example I m an expert on chairs but I can t and no one can write a program that identifies chairs in an image How can I reason rationally about a world I know nothing about How can an gain knowledge about a world without sampling it and learning from those samples Fundamental lesson of AI learned in the 1980 s Why does learning encompass reasoning Greg Grudic Machine Learning What does this mean When are ML algorithms NOT needed Tom Dietterich The goal of machine learning is to build computer systems that can adapt and learn from their experience What is Machine Learning 12 h1 h2 h K System yM y1 y2 Greg Grudic Machine Learning Output Variables y y1 y2 yK Hidden Variables h h1 h2 hK Input Variables x x1 x2 xN xN x1 x2 A Generic System 13 Greg Grudic Machine Learning Statistics mathematics theoretical computer science physics neuroscience etc These algorithms originate form many fields Machine Learning algorithms discover the relationships between the variables of a system input output and hidden from direct samples of the system Another Definition of Machine Learning 14 Greg Grudic Machine Learning This is NOT the case for almost any real system When the relationships between all system variables input output and hidden is completely understood When are ML algorithms NOT needed 15