PPT-Chapter 12 – Discriminant Analysis

Data Mining for Business Analytics Shmueli Patel amp Bruce Discriminant Analysis Background A classical statistical technique Used for classification long before data mining Classifying organisms into species. PCA Limitations of LDA Variants of LDA Other dimensionality reduction methods brPage 2br CSCE 666 Pattern Analysis Ricardo Gutierrez Osuna CSETAMU Linear discriminant analysis two classes Objective LDA seeks to reduce dimensionality while preserv 1 ANOUAR F 2 1 MEI Mars Electronics International Chemin Pontdu Centenaire 109 PlanlesOuates BP 2650 CH 1211 Genve 2 Suisse Email gastonbaudateueffemcom 2 INRASNES Institut National de Recherche en Agronomie Rue Georges Morel 49071 Beaucouz France of Computer Science UIUC dengcai2csuiucedu Xiaofei He Yahoo hexyahooinccom Jiawei Han Dept of Computer Science UIUC hanjcsuiucedu Abstract Linear Discriminant Analysis LDA has been a popular method for extracting features which preserve class separa Fisher Linear Discriminant 2 Multiple Discriminant Analysis brPage 2br CSE 555 Srihari 1 Motivation Projection that best separates the data in a least squares sense CA finds components that are useful for representing data owever no reason to assum Given . a quadratic equation use the . discriminant. to determine the nature . of the roots.. What is the discriminant?. The discriminant is the expression b. 2. – 4ac.. The value of the discriminant can be used. Why do we use the discriminant?. The discriminant tells us one of two things:. How many roots/x-intercepts/zeros does a quadratic function have?. How many solutions does a quadratic equation have?. Example. Dr J Frost (jfrost@tiffin.kingston.sch.uk) . Last modified: . 23. rd. August . 2015. Objectives: . Understand the conditions under which a quadratic equation has no, equal or distinct roots.. STARTER. Defining and Testing Groups. Goals. Develop classificatory key for groups that have already been defined. Identify important variables in defining clusters after cluster analysis. Classify new observations into an existing classification. Linear Discriminant Analysis. Objective. -Project a . feature space (a dataset n-dimensional samples) onto a smaller . -Maintain . the . class separation. Reason. -Reduce computational costs. -Minimize . Vocabulary. Discriminant - tells you how many solutions and what type you will have.. If the . discriminant is. . positive . – 2 real solutions. . negative . – 2 imaginary solutions. . zero . – 1 real solution. . for the given values:.  . 3. Sketch . the graph for each quadratic. No solutions One solution Two solutions. Using the Discriminant. I can . use the discriminant to determine how many solutions a quadratic equation will have.. CS 560 Artificial Intelligence. Many slides throughout the course adapted from Svetlana . Lazebnik. , Dan Klein, Stuart Russell, Andrew Moore, Percy Liang, Luke . Zettlemoyer. , Rob . Pless. , Killian Weinberger, Deva . Linear . Discriminant. Analysis. Chaur. -Chin Chen. Institute of Information Systems and Applications. National . Tsing. . Hua. University. Hsinchu. . 30013, Taiwan. E-mail: cchen@cs.nthu.edu.tw. Russell A. Putnam. Rehse Group. Department of Physics, University of Windsor. Windsor, Ontario, Canada. Previous paper. 2012. LIBS ON Bacteria. DFA on 13 emission lines. New study. SAME DATA BUT WITH NEW TECHNIQUES AND NEW MODELS.