This preview shows page 1. Sign up to view the full content.
Unformatted text preview: 33.1 Does SVM find a global minimum?
34 Naive Bayes, Decision Trees, K Nearest Neighbours, Boosting, and Bagging - November 25, 2009
34.1 Naive Bayes Classifiers
34.2 Decision Trees
34.2.1 Common Node Impurity Measures
34.3 K- Nearest Neighbours Classification
34.4.1 AdaBoost Algorithm
34.6.1 Random Forests wikicour senote.com/w/index.php?title= Stat841&pr intable= yes 3/74 10/09/2013 Stat841 - Wiki Cour se Notes Proposal
Mark your contribution here (http://spreadsheets.google.com/ccc?
Scribe sign up
Clas s ification
With the rise of fields such as data- mining, bioinformatics, and machine learning, classification has becomes a fast- developing topic. In the age of information, vast amounts
of data are generated constantly, and the goal of classification is to learn from data. Potential application areas include handwritten post codes recognition, medical diagnosis,
face recognition, human language processing and so on.
De finition: The problem of Prediction a discrete random variable from another random variable is called Classification. In classification,, we attempt to approximate a function , by using a training data set, which will then be able to accurately classify new data inputs.
Given , a subset of the d- dimensional real vectors and , a finite set of labels, We try to determine a 'clas s ification rule ' We use ordered pairs of training data which are identical independent distributions,
Thus, given a new input, such that, where by using the classification rule we can predict a corresponding , , to . Example Suppose we wish to classify fruits into apples and oranges by considering certain features of the fruit, for instance, color, diameter, and weight.
. The goal is to find a classification rule such that when a new fruit
based on its features,
, our classification rule can classify it as either an apple or an orange, i.e.,
View Full Document
- Winter '13