Scribd
Upload
4 views6 pages

Assignment 1 Pa

The document outlines tasks for a Thursday meeting focused on pattern analysis, including sampling algorithms, parametric vs. non-parametric density estimation, and density estimation techniques. It discusses the differences, advantages, and disadvantages of estimation methods, as well as the concepts of bias and variance in regression. Additionally, it includes practical exercises such as sketching density estimates and calculating expected values.

Uploaded by

sanxchep
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views6 pages

Assignment 1 Pa

The document outlines tasks for a Thursday meeting focused on pattern analysis, including sampling algorithms, parametric vs. non-parametric density estimation, and density estimation techniques. It discusses the differences, advantages, and disadvantages of estimation methods, as well as the concepts of bias and variance in regression. Additionally, it includes practical exercises such as sketching density estimates and calculating expected values.

Uploaded by

sanxchep
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Pattern Analysis Thursday Meeting

Juliane Ho↵mann

Worksheet 1: Thursday April 25 2024

Task 1: Sampling Algorithm


(a) Conduct the steps of the sampling algorithm for one sam-
ple using the given probability density function (pdf).

&

04

&

(b) When calculating the expected value E[f ] of f , how can sampling be useful?

Task 2: Parametric vs. Non-Parametric Density Esti-


mation
(a) What are the di↵erences between parametric vs. non-parametric density estima-
tion?
(b) What are the advantages and disadvantages of either methods?
FRI
*: 0-18
a) 0n
.

u= -
: 2

argrin P(z)
*
2 =
=
v

↓
CDF

: b) E[6] =

SfIn) h(m) di

set
of samples , .... Ru
from pin)
5-6mi) Elf]
FASK
#
Task 3: Density Estimation
Below is a copy of a 1-D distribution of points along the x-axis. Sketch a density
estimate for a box kernel on the paper. Use the y-axis to indicate the probability
mass. The bandwidth of the box kernel is 1.

Task 4: Bias and Variance in Density Estimators


(a) How is bias and variance defined in Regression?
(b) When looking at our kernel framework, how do bias and variance come into play?
FASR
I [Bom Kernel)
#SKIV
the average
(a) Bias
:Square
of deviation
of an estimator fro
t are

Variance denotes the estimates "how much the estimate


: variance
of the quantifies ,
for
a
given sample vary from one .
another

(b) large Parnel > increases bias , lowers variance .

small Rurnd - lowers bias , increases variance


.

You might also like