IT (lectures 6& 7)

Question 1

A …… is an abstraction, represented by a set of measurements describing a physical object

Answer 1

Pattern

Question 2

……. is a set of patterns sharing common attributes

Answer 2

Pattern class

Question 3

…. refers to some form of adaptation of the classification algorithm to achieve a better response

Answer 3

Learning

Question 4

…… used to reduce the classification error on a set of training data

Answer 4

Training/ learning

Question 5

If the classes to which the objects belong are known, the process is called ……..

Answer 5

Supervised learning

Question 6

If the classes to which the objects belong are unknown, the process is called ……

Answer 6

Unsupervised learning

Question 7

In ….., no labeled training sets are provided

Answer 7

Unsupervised learning

Question 8

……. is measurements of physical variables

Answer 8

Data acquisition and sensing

Question 9

Removal of noise in data is in ….. stage

Answer 9

Pre-processing

Question 10

Isolation of patterns of interest from the background is in …… stage

Answer 10

Pre-processing

Question 11

…… partitions an image into regions that are meaningful for a particular task

Answer 11

Segmentation

Question 12

….. methods, in which similarities are detected

Answer 12

Regio-based

Question 13

….. methods, in which discontinuities are detected and linked to form continuous boundaries around regions

Answer 13

Boundary-based

Question 14

Finding a new representation in terms of features is in ….. stage

Answer 14

Feature extraction

Question 15

….. are characteristic properties of the objects whose value should be similar for objects in a particular class, and different from the values for objects in another class

Answer 15

Features

Question 16

Features should be ….., they should normally be invariant to translation, orientation (rotation), scale, and illumination

Answer 16

Robust

Question 17

Features should be ……, the range of values for objects in different classes should be different and preferably be well separated and non-overlapping

Answer 17

Discriminating

Question 18

Features should be ….., all objects of the same class should have similar values

Answer 18

Reliable

Question 19

Features should be ….., uncorrelated; as a counter-example, length and area are correlated and it would be wasteful to consider both as separate features

Answer 19

Independent

Question 20

….. extracts features from raw data

Answer 20

Feature extractor

Question 21

….. is choosing the most informative subsetbof features, and removing as many irrelevant and redundant features as possible

Answer 21

Feature selection

Question 22

…… is using features and learned models to assign a pattern to a category

Answer 22

Classification

Question 23

……. assigns objects to certain categories (or classes) based on the feature information

Answer 23

Classification

Question 24

Evaluation of confidence in decisions is in ….. stage

Answer 24

Post-processing

Question 25

K-Nearest Neighbor is an example of .....

Answer 25

Classification

Question 26

K-Means is an example of .....

Answer 26

Clustering

Question 27

...... stores all available cases and classifies new cases based on a similarity measure

Answer 27

K-Nearest Neighbor

Question 28

Lazy learning algorithm

Answer 28

K-Nearest Neighbor