Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Learning Problems & Basics

Total questions: 50

Worksheet time: 25mins

Name
Class
Date
1.

A learning problem is defined by which three components?

a)

Input, Output, Memory

b)

Algorithm, Data, Result

c)

Knowledge, Skill, Ability

d)

Task, Performance, Experience

2.

The task in a learning problem refers to:

a)

Training data

b)

What the system should learn to do

c)

Accuracy measure

d)

Output format

3.

Performance measure evaluates:

a)

Learning speed

b)

Type of algorithm

c)

Size of dataset

d)

Success of learning

4.

Training experience mainly consists of:

a)

Heuristics

b)

Goals

c)

Examples or data

d)

Rules

5.

Learning from labeled data is called:

a)

Unsupervised learning

b)

Reinforcement learning

c)

Supervised learning

d)

Heuristic learning

6.

Learning improves system performance by:

a)

Experience

b)

Memorization only

c)

Hard coding

d)

Guessing

7.

A learning agent adapts based on:

a)

Experience

b)

Errors

c)

Rules

d)

Memory size

8.

Which is NOT a learning problem component?

a)

Compiler

b)

Task

c)

Experience

d)

Performance

9.

Email spam detection is an example of:

a)

Learning

b)

Planning

c)

Reasoning

d)

Searching

10.

Machine learning mainly focuses on:

a)

Programming rules

b)

Hardware design

c)

Manual coding

d)

Learning from data

11.

One key issue in learning systems is:

a)

All of the above

b)

Overfitting

c)

Data scarcity

d)

Data representation

12.

One key issue in learning systems is:

a)

All of the above

b)

Overfitting

c)

Data scarcity

d)

Data representation

13.

Overfitting occurs when a model:

a)

Performs poorly on training data

b)

Has fewer features

c)

Performs well only on training data

d)

Performs well on new data

14.

Generalization means:

a)

Applying learned knowledge to unseen data

b)

Memorizing data

c)

Removing features

d)

Reducing data size

15.

Bias in learning refers to:

a)

Preference for certain hypotheses

b)

Noise

c)

Random choice

d)

Error in data

16.

Noise in data can cause:

a)

No effect

b)

Faster training

c)

Overfitting

d)

Perfect learning

17.

Concept learning involves:

a)

Learning algorithms

b)

Learning rules or categories

c)

Learning hardware

d)

Learning functions

18.

A concept can be represented as:

a)

Set of objects

b)

Boolean function

c)

Rule

d)

All of the above

19.

Positive examples are:

a)

Negative samples

b)

Errors

c)

Instances belonging to the concept

d)

Incorrect data

20.

Negative examples are:

a)

Instances not belonging to the concept

b)

Correct instances

c)

Training data only

d)

Output data

21.

Concept learning is mainly used in:

a)

Planning

b)

Searching

c)

Classification

d)

Sorting

22.

Version space is defined as:

a)

All possible algorithms

b)

Set of all hypotheses

c)

Hypotheses consistent with training data

d)

Final hypothesis

23.

Candidate Elimination algorithm finds:

a)

Single hypothesis

b)

Optimal tree

c)

Entire version space

d)

Only general hypothesis

24.

The most specific hypothesis is stored in:

a)

G boundary

b)

Training set

c)

Version space

d)

S boundary

25.

The most general hypothesis is stored in:

a)

S boundary

b)

Memory

c)

Dataset

d)

G boundary

26.

Candidate Elimination works with:

a)

Only positive examples

b)

Unlabeled data

c)

Only negative examples

d)

Both positive and negative examples

27.

Version space is defined as:

a)

All possible algorithms

b)

Final hypothesis

c)

Set of all hypotheses

d)

Hypotheses consistent with training data

28.

Candidate Elimination algorithm finds:

a)

Single hypothesis

b)

Only general hypothesis

c)

Optimal tree

d)

Entire version space

29.

Candidate Elimination works with:

a)

Unlabeled data

b)

Only positive examples

c)

Only negative examples

d)

Both positive and negative examples

30.

S boundary represents:

a)

Most specific hypotheses

b)

Most general hypotheses

c)

Random hypotheses

d)

Invalid hypotheses

31.

G boundary represents:

a)

Most specific hypotheses

b)

Final hypothesis

c)

Most general hypotheses

d)

Training examples

32.

Version space becomes empty when:

a)

Dataset is large

b)

Learning completes

c)

Hypotheses conflict

d)

Data is consistent

33.

Main drawback of Candidate Elimination is:

a)

Complexity

b)

Sensitivity to noise

c)

Slow speed

d)

Memory usage

34.

Inductive bias is:

a)

Data error

b)

Learning preference

c)

Output error

d)

Algorithm speed

35.

Bias helps in:

a)

Removing data

b)

Increasing noise

c)

Random guessing

d)

Limiting hypothesis space

36.

Decision tree bias prefers:

a)

Deeper trees

b)

Larger datasets

c)

Smaller trees

d)

Random trees

37.

Inductive bias affects:

a)

Hardware

b)

Learning outcome

c)

Output format

d)

Input size

38.

Decision tree bias prefers: A) Deeper trees B) Smaller trees C) Random trees D) Larger datasets

a)

Larger datasets

b)

Smaller trees

c)

Random trees

d)

Deeper trees

39.

Inductive bias affects: A) Learning outcome B) Input size C) Output format D) Hardware

a)

Hardware

b)

Output format

c)

Input size

d)

Learning outcome

40.

A decision tree is used for: A) Sorting B) Classification C) Searching D) Scheduling

a)

Classification

b)

Sorting

c)

Searching

d)

Scheduling

41.

Internal nodes represent: A) Output labels B) Decisions/tests C) Data D) Rules

a)

Data

b)

Rules

c)

Output labels

d)

Decisions/tests

42.

Leaf nodes represent: A) Attributes B) Conditions C) Class labels D) Algorithms

a)

Algorithms

b)

Conditions

c)

Class labels

d)

Attributes

43.

ID3 algorithm uses: A) Entropy B) Information Gain C) Gini index D) Accuracy

a)

Gini index

b)

Information Gain

c)

Entropy

d)

Accuracy

44.

Representation in learning means: A) Data storage B) Knowledge encoding C) Output format D) Algorithm selection

a)

Knowledge encoding

b)

Output format

c)

Algorithm selection

d)

Data storage

45.

Heuristic is: A) Exact solution B) Rule of thumb C) Random guess D) Dataset

a)

Exact solution

b)

Rule of thumb

c)

Random guess

d)

Dataset

46.

Heuristic search improves: A) Accuracy B) Speed of search C) Memory D) Data size

a)

Speed of search

b)

Memory

c)

Accuracy

d)

Data size

47.

Best-first search uses: A) Random selection B) FIFO C) Heuristic evaluation D) Stack

a)

FIFO

b)

Stack

c)

Heuristic evaluation

d)

Random selection

48.

A algorithm is:* A) Blind search B) Heuristic search C) Random search D) Exhaustive search

a)

Heuristic search

b)

Blind search

c)

Exhaustive search

d)

Random search

49.

Heuristic function estimates: A) Exact cost B) Remaining cost C) Data size D) Accuracy

a)

Accuracy

b)

Remaining cost

c)

Exact cost

d)

Data size

50.

Heuristic search is mainly used in: A) Optimization problems B) Sorting C) File handling D) Compilation

a)

Sorting

b)

File handling

c)

Optimization problems

d)

Compilation