tailieunhanh - Artificial Intelligence - Lecturer 13: Machine Learning

Introduction of Machine learning: Definitions of Machine learning, representation of the learning problem, application examples of ML, key elements of a ML problem, issues in Machine Learning, types of learning problems. | 5 28 2014 Artificial Intelligence For HEDSPI Project Lecturer 13 - Machine Learning Lecturers Thanh Huong Duc Khanh Dr. Hai V. Pham HUST 1 Introduction of Machine learning Definitions of Machine learning. A process by which a system improves its performance Simon 1983 Any computer program that improves its performance at some task through experience Mitchell 1997 Programming computers to optimize a performance criterion using example data or past experience Alpaydin 2004 Representation of the learning problem Mitchell 1997 Learning Improving with experience at some task Improve over task T With respect to performance measure P Based on experience E 2 1 5 28 2014 Application examples of ML 1 Web pages filtering problem T to predict which Web pages a given user is interested in P of Web pages correctly predicted E a set of Web pages identified as interested uninterested for the user Web pages categorization problem T to categorize Web pages in predefined categories P of Web pages correctly categorized E a set of Web pages with specified categories __I Business __I Entertainment o Science o Sports __I Technology ã Travel Tourism Application examples of ML 2 Handwriting recognition problem T to recognize and classify handwritten words within images P of words correctly classified E a database of handwritten words with given classifications . labels Robot driving problem T to drive on public highways using vision sensors P average distance traveled before an error as judged by human overseer E a sequence of images and steering commands recorded while observing a human driver Which steering command Go Move Move Slow Speed straight left right down up 4 2 5 28 2014 Key elements of a ML problem 1 Selection of the training examples Direct or indirect training feedback With teacher . with labels or without The training examples set should be representative of the future test examples Choosing the target function . hypothesis concept etc. F X 0 1 F X a