Wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

AIM Review

Total questions: 40

Worksheet time: 20mins

Name
Class
Date
1.
What is a Greedy Algorithm?
a)
binary decision process based on Gini Index
b)
path selection based on local optimization
c)
maximization of residual errors
d)
minimizes euclidean distance when clustering
2.
Greedy approach...
a)
is always the best problem solving method
b)
picks the most optimal solution
c)
picks the local most optimal solution
d)
breaks bigger problem into smaller ones
e)
None
3.
A greedy algorithm can be used to solve all the dynamic programming problems.
a)
True
b)
False
4.
Ant colony optimization
a)
Is not able to solve the TSP
b)
All initial directions are randomly selected
c)
Learning happens by the amount of pheromone in each path
d)
Considers the quality of food source and length of the path
e)
None
5.
Which one below is NOT the application of Ant Colony Optimization (ACO)?
a)
traffic congestion and control
b)
security and crytography
c)
structural optimization
d)
optimization in manufacturing, and genomics
e)
None
6.

Ant colony behavior is mainly based on...

a)

the exploitation of proactive feedback

b)

the exploitation of neutral feedback

c)

the exploitation of positive feedback

d)

the exploitation of negative feedback

e)

None

7.
Optimization is performed by
a)
Artificial Neural Network
b)
Genetic Algorithm
c)
Correlation
d)
Decision tree
e)
None
8.
The simulated annealing algorithm...
a)
decreases the temp, accepting better solns as time goes on
b)
decreases the temp, accepting worse solns as time goes on
c)
increases the temp, accepting better solns as time goes on
d)
None
e)
None
9.
What is Machine Learning?
a)
Selective acquisition of knowledge using computer programs
b)
Autonomous acquisition of knowledge using manual programs
c)
Autonomous acquisition of knowledge using computer programs
d)
Selective acquisition of knowledge using manual programs
e)
None
10.
What is Machine learning?
a)
Is the same of Artificial Intelligence
b)
is a subset of artificial intelligence
c)
is when multimple Artificial Intelligences are combined
d)
Is a software that performs automated analysis
e)
None
11.
What is Machine Learning?
a)
An algorithm that performs a specific task by studying patterns
b)
A machine humans can learn from
c)
A machine that draws conclusions from its environment
d)
None of the above
e)
None
12.
The Most Common Machine Learning Type
a)
Unsupervised
b)
Unmanned
c)
Supervised
d)
Reinforcement
e)
None
13.
Why is machine learning powerful?
a)
It's not. Don't trust the Machine. Skynet is coming.
b)
Scale and Reach
c)
Better creative output.
d)
Trusting the machine means you can focus more on strategy
e)
None
14.
What is a Classifier in Machine Learning?
a)
An algorithm technique
b)
An approach in machine learning
c)
An algorithm in machine learning
d)
A function or a system that maps input data to a category
e)
None
15.
What is semantic?
a)
cueing system which is grammar based
b)
cueing system which relies on letter-sound relationships
c)
cueing system which relies on meaning and vocabulary
d)
cueing system which relies on practical use of language
e)
None
16.
What is pragmatic?
a)
cueing system which is grammar based
b)
cueing system which relies on letter-sound relationships
c)
cueing system which relies on meaning and vocabulary
d)
cueing system which relies on practical use of language
e)
None
17.
Phonemes refer to
a)
babies' babble at first
b)
the sounds that are possible for humans to make
c)
the sounds of language
d)
differences across languages
e)
None
18.
What is a lemma?
a)
the stem of a word
b)
an animal living in the Andes Mountains
c)
A heading indicating the subject or argument
d)
A word / phrase defined in a dictionary / entry word list
e)
None
19.
A grammar that produces more than one parse tree for some sentence is called
a)
Ambiguous
b)
Regular
c)
Unambiguous
d)
None of the mentioned
e)
None
20.

Open Loop System

a)

System output has no effect on the control

b)

System output has an effect on control

c)

This is not the right answer

d)

Goes in an infinite loop

21.

Is a microwave an example of an open or closed loop system?

a)

Open

b)

Closed

22.

Is a thermostat an example of an open or closed loop system?

a)

Open

b)

Closed

23.

Is a racing cyclist an example of an open or closed loop system?

a)

Open

b)

Closed

24.

Is the cruise control on a car an example of an open or closed loop system?

a)

Open

b)

Closed

25.

Is an old washer and dryer an example of an open or closed loop system?

a)

Open

b)

Closed

26.

Is a modern washing machine an example of an open or closed loop system?

a)

Open

b)

Closed

27.

The number of moveable joints in the base, the arm, and the end effectors of the robot determines_________

a)

a) degrees of freedom

b)

b) payload capacity

c)

c) operational limits

d)

d) flexibility

28.
What Problems do ANNs not solve?
a)
Geometric problems
b)
Science problems
c)
Industry problems
d)
Financial problems
29.

The main application of convolutional neural networks is?

a)

Image recognition

b)

Finding local maximum

c)

weather predictions

d)

Image classification

30.

What if we would like to have prediction output (binary classification) represented by probability, which activation function is the best choice?

a)

tanh

b)

ReLu

c)

Sigmoid

d)

Linear

31.

What if the learning rate is too high?

a)

Model is difficult to converge

b)

Model consumes more computational resources

c)

Model takes longer time to converge

d)

Model is difficult to generalize

32.

Which of the following is not used to reduce overfitting?

a)

Stopping the training earlier

b)

Using a larger dataset

c)

Reducing the complexity of the model

d)

Using k-fold cross validation

33.

Which of the following statements is false?

a)

Overfitted models perform better on the training data than on the test data

b)

Overfitting can occur when learning is performed for too long

c)

Overfitting can occur if the training set is not representative

d)

Underfitted models always generalise well to different datasets

34.

What is the purpose of a loss function in machine learning?

a)

To increase the model's accuracy

b)

To speed up the training process

c)

To measure the model's error

d)

To define the output of the model

35.

Which of the following is not a popular machine learning library or framework?

a)

TensorFlow

b)

PyTorch

c)

Keras

d)

Microsoft Word

36.

What is overfitting in machine learning?

a)

Achieving high model accuracy

b)

Fitting the model to the training data too closely

c)

Underutilizing the training data

d)

Reducing the model's complexity

37.

What is reinforcement learning in the context of AI, and provide an example application?

a)

Reinforcement learning is the process of training AI models with supervised data. An example application is image classification.

b)

Reinforcement learning is the process of training AI models with labeled data. An example application is autonomous driving.

c)

Reinforcement learning is the process of learning from interaction with an environment to maximize rewards. An example application is training a robot to play chess.

d)

Reinforcement learning is the process of using pre-defined rules to make AI decisions. An example application is spam email filtering.

38.

What is the term for a machine learning technique that involves combining multiple models to improve overall performance?

a)

Ensemble Learning

b)

Gradient Descent

c)

Reinforcement Learning

d)

Unsupervised Learning

39.

What is the main difference between classification and regression tasks in machine learning?

a)

Classification predicts categories, while regression predicts numerical values.

b)

Classification uses neural networks, while regression uses decision trees.

c)

Classification is supervised learning, while regression is unsupervised learning.

d)

Classification involves clustering data, while regression involves linear equations.

40.

What does the term "bias-variance trade-off" refer to in machine learning?

a)

Balancing the model's accuracy with its interpretability

b)

The trade-off between underfitting and overfitting

c)

The balance between feature selection and feature engineering

d)

The trade-off between training time and prediction time