Download presentation
Presentation is loading. Please wait.
Published byShanon Lucas Modified over 9 years ago
1
Machine Learning 10601 Recitation 6 Sep 30, 2009 Oznur Tastan
2
Outline Multivariate Gaussians Logistic regression
3
Multivariate Gaussians (or "multinormal distribution“ or “multivariate normal distribution”) Multivariate case: Vector of observations x, vector of means and covariance matrix Univariate case: single mean and variance Dimension of xDeterminant
4
Multivariate Gaussians do not depend on x normalization constants Multivariate case Univariate case depends on x and positive
5
The mean vector
6
Covariance of two random variables Recall for two random variables x i, x j
7
The covariance matrix transpose operator Var(x m )=Cov(x m, x m )
8
An example: 2 variate case The pdf of the multivariate will be: Covariance matrix Determinant
9
An example: 2 variate case Recall in general case independence implies uncorrelation but uncorrelation does not necessarily implies independence. Multivariate Gaussians is a special case where uncorrelation implies independence as well. Factorized into two independent Gaussians! They are independent!
10
Diagonal covariance matrix Diagonal matrix: m matrix where off-diagonal terms are zero If all the variables are independent from each other, The covariance matrix will be an diagonal one. Reverse is also true: If the covariance matrix is a diagonal one they are independent
11
Gaussian Intuitions: Size of = [0 0] = [0 0] = [0 0] = I = 0.6 I = 2 I As becomes larger, Gaussian becomes more spread out Identity matrix
12
Gaussian Intuitions: Off-diagonal As the off-diagonal entries increase, more correlation between value of x and value of y
13
Gaussian Intuitions: off-diagonal and diagonal Decreasing non-diagonal entries (#1-2) Increasing variance of one dimension in diagonal (#3)
14
Isocontours
15
Isocontours example We have showed Now let’s try to find for some constant c the isocontour
16
Isocontours continued
17
Define Equation of an ellipse Centered on μ 1, μ 2 and axis lengths 2r 1 and 2r 2
18
We had started with diaogonal matrix In the diagonal covariance matrix case the ellipses will be axis aligned.
19
Don’t confuse Multivariate Gaussians with Mixtures of Gaussians Mixture of Gaussians: Component Mixing coefficient K=3
20
Logistic regression Linear regression Outcome variable Y is continuous Logistic regression Outcome variable Y is binary
21
Logistic function (Logit function) z logit(z) Notice σ(z) is always bounded between [0,1] (a nice property) and as z increase σ(z) approaches 1, as z decreases σ(z) approaches to 0 This term is [0, infinity]
22
Logistic regression Learn a function to map X values to Y given data The function we try to learn is P(Y|X) X can be continuous or discrete Discrete
23
Logistic regression
24
Classification If this holds Y=0 is more probable Than Y=1 given X
25
Classification Take log both sides Classification rule if this holds Y=0
26
Logistic regression is a linear classifier Y=0 Y=1 Decision boundary
27
Classification X1 σ(z)= σ(w 0 +w 1 X 1 )) Notice σ(z) is 0.5 when X1=2 wo=+2, to check evaluate at X1=0 g(z)~0.1 σ(z) is 0.5 when X1=0 to see Classify as Y=0
28
Estimating the parameters Given data Objective: Train the model to get w that maximizes the conditional likelihood
29
Difference with Naïve Bayes of Logistic Regression Loss function! Optimize different functions → Obtain different solutions Naïve Bayes argmax P(X|Y) P(Y) Logistic Regression argmax P(Y|X)
30
Naïve Bayes and Logistic Regression Have a look at the Tom Mitchell’s book chapter http://www.cs.cmu.edu/%7Etom/mlbook/NBayesLogReg.pdf Linked under Sep 23 Lecture Readings as well.
31
Some matlab tips for the last question in HW3 logical function might be useful for dividing into splits. An example of logical in use (please read the Matlab help) S=X(logical(X(:,1)==1),:) this will also work S=X((X(:1)==1,:)) This will subset the portion of the X matrix where the first column has value 1 and will put in matrix S (like Data>Filter in Excel) Matlab has functions for mean, std, sum, inv, log2 Scaling data to zero mean and unit variance: shifting the mean by the mean (subtracting the mean from every element of the vector) and scaling such that it has variance=1 ( dividing the every element of the vector by standard deviation) To be able to do that in matrices. You will need the repmat function, have a look at that otherwise the size of the matrices would not match..etc Elementwise multiplication use.*
32
References http://www.stanford.edu/class/cs224s/lec/224s.09.lec10.pdf http://www.stanford.edu/class/cs224s/lec/224s.09.lec10.pdf http://www.cs.cmu.edu/%7Etom/mlbook/NBayesL ogReg.pdf Carlos Guestrin lecture notes Andrew Ng lecture notes
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.