wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Module-1

Total questions: 10

Worksheet time: 6mins

Name
Class
Date
1.

The symbol used to represent a board state, score assigned to it

a)

<>

b)

{}

c)

()

d)

[]

2.

The set of examples are represented as

a)

Ordered Pair

b)

Ordered List

c)

Ordered Set

d)

Ordered Items

3.

LMS is

a)

Least Mean Square

b)

List Mean Sqaure

c)

Least Max Square

d)

Least Mass Sqaure

4.

Is there any fixed number of features to represent the target function?

a)

No,it is task specific.

b)

Yes, it is same fixed number of features for all tasks.

c)

Cann't say.

d)

None

5.

Are the features are important to represent the target function?

a)

Very important

b)

Not important

c)

Not requried

d)

None

6.

What is the sequence of designing a learning system?

a)

Well posed problem,target function,representation target function,Choosing experience,Function approximation algorithm

b)

Well posed problem,Choosing experience,target function,representation target function,Function approximation algorithm

c)

Well posed problem,Choosing experience,representation target function,target function,Function approximation algorithm

d)

Well posed problem,Choosing experience,representation target function,Function approximation algorithm,target function

7.

What are the following is required for define well posed problem in our discussion of learning system?

a)

Task,Performance,Experience

b)

Task,Efficiency, Example

c)

Task, Ability,Errors

d)

None

8.

Which of the following describe 'Learner' in machine learning?

a)

Computer program

b)

Algorithm

c)

Student

d)

None

9.

What is the purpose o the error caluclation in learning system?

a)

To know how good our algorithm is working

b)

To know at what extent we have to train weights

c)

To know what is avg error of the proposed algorithm

d)

None

10.

The weight update rule is

a)

W.new = W.old + η(Acutalvalue predictedvalue)W.new\ =\ W.old\ +\ \eta\left(Acutalvalue\ -\ predictedvalue\right)

b)

W.new = W.old + (0.1)(Acutalvalue Predictedvalue)W.new\ =\ W.old\ +\ \left(0.1\right)\cdot\left(Acutalvalue\ -\ \Pr edictedvalue\right)

c)

W.new = W.old (η)(Actualvalue PredictedValue)W.new\ =\ W.old\ -\ \left(\eta\right)\cdot\left(Actualvalue\ -\ \Pr edictedValue\right)

d)

W.new = W.old (0.1)(Acutalvalue predictedvalue)W.new\ =\ W.old\ -\ \left(0.1\right)\cdot\left(Acutalvalue\ -\ predictedvalue\right)