Linear Regression - University of Pennsylvania
[Pages:61]Linear Regression
These slides were assembled by Eric Eaton, with grateful acknowledgement of the many others who made their course materials freely available online. Feel free to reuse or adapt these slides for your own academic purposes, provided that you include proper aHribuIon. Please send comments and correcIons to Eric.
Robot Image Credit: Viktoriya Sukhanova ?
Regression
Given:
? Data
X
n
o
= (1), . . . , (n)
x
x
where
(i) 2 Rd x
? Corresponding labels
n
o
y = y(1), . . . , y(n)
where
y(i)
2R
9
September Arc+c Sea Ice Extent (1,000,000 sq km)
8
7
6
5
4
3 Linear Regression QuadraIc Regression
2
1
0 1975
1980
1985
1990
1995 Year
2000
2005
2010
2015
Data from G. WiH. Journal of StaIsIcs EducaIon, Volume 21, Number 1 (2013)
2
Prostate Cancer Dataset
? 97 samples, parIIoned into 67 train / 30 test ? Eight predictors (features):
? 6 conInuous (4 log transforms), 1 binary, 1 ordinal
? ConInuous outcome variable:
? lpsa: log(prostate specific anIgen level)
Based on slide by Jeff Howbert
Linear Regression
? Hypothesis:
Xd
y = 0 + 1x1 + 2x2 + . . . + dxd = j xj
j=0 Assume x0 = 1
? Fit model by minimizing sum of squared errors
x
Figures are courtesy of Greg Shakhnarovich
5
Least Squares Linear Regression
?
Cost FuncIon J( ) =
1 2n
Xn
h
(i)
x
i=1
? Fit by solving min J()
2 y(i)
6
IntuiIon Behind Cost FuncIon
J( )
=
1 2n
Xn h
(i)
x
i=1
2 y(i)
For insight on J(), let's assume x 2 R so = [0, 1]
Based on example
by Andrew Ng
7
IntuiIon Behind Cost FuncIon
J( )
=
1 2n
Xn h
(i)
x
i=1
2 y(i)
For insight on J(), let's assume x 2 R so = [0, 1]
(for fixed , this is a funcIon of x)
3
2
y
1
0
0
1x 2
3
Based on example by Andrew Ng
(funcIon of the parameter )
3 2 1 0 -0.5 0 0.5 1 1.5 2 2.5
8
IntuiIon Behind Cost FuncIon
J( )
=
1 2n
Xn h
(i)
x
i=1
2 y(i)
For insight on J(), let's assume x 2 R so = [0, 1]
(for fixed , this is a funcIon of x)
3
(funcIon of the parameter )
3
2
2
y
1
1
0 0
Based on example by Andrew Ng
0
1x 2
3
-0.5 0 0.5 1 1.5 2 2.5
J([0, 0.5]) =
1
(0.5
1)2 + (1
2)2 + (1.5
3)2 0.58
23
9
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- linear regression university of pennsylvania
- multiple linear regression analysis across fmri 3d datasets
- evaluating aptness of a regression model taylor francis
- fast privacy preserving linear regression over distributed datasets
- multiple linear regression in minitab new york university
- predicting movie revenue from imdb data stanford university
- chapter 2 simple linear regression analysis the simple linear
- project linear correlation and regression central oregon community
- when can multi site datasets be pooled for regression hypothesis tests
- this video will discuss some scipy tools that assess associations among
Related searches
- university of pennsylvania finance depart
- university of pennsylvania finance program
- university of pennsylvania finance department
- university of pennsylvania finance master
- university of pennsylvania masters programs
- university of pennsylvania online masters
- university of pennsylvania online programs
- university of pennsylvania wharton
- linear regression coefficient of determination
- university of pennsylvania mba tuition
- university of pennsylvania graduate programs
- university of pennsylvania phd programs