Many pattern recognition problems require the original input variables to be combined together to make a smaller number of new variables. These new input variables are called

a$)$ patterns b$)$ features c$)$ weights d$)$ classes

$-----------------------------------------------------------------------------------------------------------------$

$2)$ The process described in Question $1$ is

a$)$ a type of pre$-$processing which is often called feature extraction.

b$)$ a type of pattern recognition which is often called classification.

c$)$ a type of post$-$processing which is often called winner$-$takes$-$all.

$-----------------------------------------------------------------------------------------------------------------$

$3)$ Is the following statement true or false? $$In supervised learning, there is a target output

vector that tells the pattern recognition system the correct class for a given input

vector.$$

$-----------------------------------------------------------------------------------------------------------------$

$4)$ For a minimum distance classifier with three input variables, what is the decision

Boundary between two classes?

a$)$ A line.; b$)$ A curve. ; c$)$ A plane. ; d$)$ A hyperplane. ; e$)$ A discriminant value.

$-----------------------------------------------------------------------------------------------------------------$

$5)$ A training pattern, consisting of an input vector and desired outputs $,$ is presented to the following neural network. What is the usual sequence of events for training the network using the backpropagation algorithm?